© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 226806 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
226806

INDEX

Explanations

obtain authorization

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

诟

0.49

rick

0.48

рты

0.48

Muy

0.48

вым

0.46

𝓶

0.46

 devising

0.46

י

0.46

бах

0.45

 uttering

0.45

POSITIVE LOGITS

 Raffle

0.49

 December

0.45

 Cardiff

0.44

obtain

0.42

follows

0.42

 January

0.42

0.42

0.41

 Indigenous

0.41

 February

0.41

Activations Density 0.001%

No Known Activations