© 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-3-4B-IT · 9-GEMMASCOPE-2-RES-262K · 12001 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-262K
12001

INDEX

Explanations

CEO

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_262k_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

Not in Any Lists

No Comments

Negative Logits

3.21

 erasure

2.71

الع

2.61



2.61

 สืบค้น

2.52

🤏

2.50

 restos

2.39

🫠

2.37

 digress

2.34

‬‬

2.33

POSITIVE LOGITS

cej

2.56

skaya

2.53

otically

2.18

ILITY

2.15

roph

2.11

razier

2.03

ringer

2.03

 Yeah

2.02

ference

2.01

𝐧

2.00

Activations Density 0.004%

No Known Activations