© 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-3-4B-IT · 9-GEMMASCOPE-2-RES-16K · 362 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-16K
362

INDEX

Explanations

well wishes

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium

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

Negative Logits

ities

1.74

бира

1.37

 supra

1.36

ামুটি

1.35

 whopping

1.34

ب

1.30

 Elli

1.30

ﺏ

1.28

্চ

1.28

 प्रसिद्ध

1.26

POSITIVE LOGITS

1.35

जनक

1.34

 quotient

1.26

readdir

1.21

 দুর্দ

1.20

eid

1.19

ingly

1.18

Euler

1.16

্লীল

1.16

Deserialize

1.13

Activations Density 0.906%

No Known Activations