© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 41-GEMMASCOPE-2-RES-262K · 353 ｜ Neuronpedia

Home
Gemma-3-27B-IT
41-GEMMASCOPE-2-RES-262K
353

INDEX

Explanations

units of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ូត

0.47

 seasonings

0.47

বিষ্য

0.46

 flavoring

0.45

 moistened

0.44

飲料

0.43

 harmonics

0.43

繁忙時間

0.43

溶液

0.42

 प्याज

0.42

POSITIVE LOGITS

 Physical

0.58

 Structural

0.58

Hardware

0.57

 직접

0.55

Structural

0.55

Local

0.55

Physical

0.55

 hardcore

0.54

 melee

0.53

傳統

0.53

Activations Density 0.001%

No Known Activations