© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-2-27B · 34-GEMMASCOPE-RES-131K · 88 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
88

INDEX

Explanations

news and media outlets

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

inguishing

-0.75

esca

-0.71

rientes

-0.70

Tier

-0.70

BJP

-0.69

 behalten

-0.69

 canoe

-0.68

voj

-0.68

intracht

-0.67

}{*}{}

-0.67

POSITIVE LOGITS

 CNBC

1.48

NBC

0.91

″

0.84

🦟

0.81

ῦ

0.78

cnbc

0.77

CN

0.77

 Gout

0.76

 wektor

0.76

NBC

0.75

Activations Density 0.009%

No Known Activations