© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 34-GEMMASCOPE-RES-131K · 108964 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
108964

INDEX

Explanations

'-----Original Message-----'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cades

-0.78

لح

-0.72

촌

-0.68

ЧЕСКИ

-0.67

naux

-0.66

جمه

-0.66

jaj

-0.66

Kl

-0.65

filterBy

-0.65

 anxious

-0.64

POSITIVE LOGITS

 Formal

0.67

erial

0.63

 Sarac

0.62

 càng

0.62

पू

0.62

峽

0.62

Shiv

0.62

zufügen

0.61

遭遇

0.61

 hút

0.60

Activations Density 0.104%

No Known Activations