© 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 · 9-GEMMASCOPE-2-RES-262K · 8499 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-262K
8499

INDEX

Explanations

query parameters

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

इसके

1.46

न

1.38

ಗ್ಗ

1.34

 dites

1.31

오

1.28

й

1.27

𝙞

1.26

 pleural

1.25

ooo

1.25

 promedio

1.23

POSITIVE LOGITS

 Hundreds

1.53

क

1.50

০

1.44

onant

1.41

BLIC

1.40

 pious

1.39

 intelligents

1.38

ĩa

1.37

arono

1.37

 carriages

1.36

Activations Density 0.029%

No Known Activations