© 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 · 29-GEMMASCOPE-2-RES-65K · 2272 ｜ Neuronpedia

Home
Gemma-3-4B-IT
29-GEMMASCOPE-2-RES-65K
2272

INDEX

Explanations

No Explanations Found

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

noduch

0.76

}\|

0.74

ąć

0.69

 пробле

0.69

 कहकर

0.69

 yapılacak

0.68

ambilan

0.68

sgál

0.67

<unused72>

0.66

ంటి

0.66

POSITIVE LOGITS

 over

3.77

 since

3.10

 throughout

2.89

 Over

2.77

Over

2.76

over

2.64

since

2.51

 sejak

2.46

 منذ

2.44

 OVER

2.39

Activations Density 0.608%

No Known Activations