Google DeepMind · Gemma 2

Gemma 2 27B IT

READER SUMMARY

Google DeepMind's instruction-tuned 27B Gemma 2 checkpoint, released through downloadable weights and immediately supported across major developer platforms.

DOOM SCORE59.6out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 59.6

High mid-tier capability, instruction following and broad open-weight access produce substantial deployment and misuse potential with weak post-release control.

Capability64
Autonomy12
Deployment95
Misuse potential61
Control difficulty67
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Gemma 2 27B IT

The model score of 59.6 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.01

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

CapabilityTOWARD

Google releases Gemma 2 9B and 27B open models

Google released Gemma 2 base and instruction-tuned checkpoints at 9B and 27B parameters, with downloadable weights, broad toolchain support and immediate access through AI Studio and other platforms.

Full item contribution
+0.03
Gemma 2 27B IT equal share
+0.01
Read assessment →
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 59.6

    New exact Gemma 2 27B instruction-tuned checkpoint.

    12 Aug 2026