© 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 · 77531 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
77531

INDEX

Explanations

making eye contact

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

 GlobalKey

-0.75

ёр

-0.74

 guadag

-0.73

 fonde

-0.73

ံ

-0.72

孪

-0.69

 getDescription

-0.69

🔙

-0.68

 שא

-0.68

 Raad

-0.67

POSITIVE LOGITS

eye

5.38

eye

3.91

Eye

3.66

Eye

3.53

EYE

3.06

EYE

2.98

ey

2.44

 eyeball

2.06

 Augen

2.03

眼

2.00

Activations Density 0.053%

No Known Activations