© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-4B-IT · 22-GEMMASCOPE-2-RES-262K · 5125 ｜ Neuronpedia

Home
Gemma-3-4B-IT
22-GEMMASCOPE-2-RES-262K
5125

INDEX

Explanations

along the way

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_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

ících

0.62

뚤

0.62

constr

0.61

IOP

0.61

AID

0.60

ాలంటే

0.60

<unused69>

0.59

 appendages

0.58

>::

0.58

 fuzz

0.58

POSITIVE LOGITS

way

1.45

 unterwegs

1.31

דרך

1.24

 Along

1.20

 route

1.19

way

1.16

WAY

1.12

 camino

1.12

 along

1.11

 caminho

1.11

Activations Density 0.026%

No Known Activations