© 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 · 22-GEMMASCOPE-2-RES-65K · 8874 ｜ Neuronpedia

Home
Gemma-3-4B-IT
22-GEMMASCOPE-2-RES-65K
8874

INDEX

Explanations

please read disclaimer

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_22_width_65k_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

 please

1.93

请

1.75

plz

1.71

Please

1.71

 Please

1.70

please

1.52

 bitte

1.48

pls

1.42

請

1.40

Bitte

1.33

POSITIVE LOGITS

 deformation

1.21

Nxe

1.19

 distorted

1.14

 conventional

1.13

ee

1.12

 distortion

1.12

वन

1.10

 parks

1.10

みた

1.09

oners

1.07

Activations Density 0.029%

No Known Activations