© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 72249 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
72249

INDEX

Explanations

gray concrete, may walk

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

Controlled Header

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

Not in Any Lists

No Comments

Negative Logits

 hablar

0.47

द्धाल

0.46

研究

0.45

⚤

0.44

ONEDB

0.43

ാര്‍

0.43

яд

0.43

 afectar

0.43

ৌশ

0.42

𝔪

0.42

POSITIVE LOGITS

0.51

،

0.48

----------------

0.48

ی

0.47

دی

0.45

 ہل

0.44

↵

0.43

Pot

0.43

ھی

0.43

 میر

0.42

Activations Density 0.000%

No Known Activations