© 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 · 29-GEMMASCOPE-2-RES-65K · 2143 ｜ Neuronpedia

Home
Gemma-3-4B-IT
29-GEMMASCOPE-2-RES-65K
2143

INDEX

Explanations

whilst whereas promptly

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_29_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

Not in Any Lists

No Comments

Negative Logits

)^{-

0.68

 જોડ

0.61

এর

0.61

ada

0.59

 saya

0.58

Sig

0.57

นำ

0.57

có

0.56

డ

0.54

 পেলাম

0.54

POSITIVE LOGITS

 whilst

1.34

1.27

 whereas

1.24

 Whilst

1.23

 effortlessly

1.19

!.

1.14

 inside

1.14

 whenever

1.14

 promptly

1.14

Whilst

1.13

Activations Density 0.001%

No Known Activations