© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-2-27B · 34-GEMMASCOPE-RES-131K · 37831 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
37831

INDEX

Explanations

William Muldoon

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

 pekan

-0.75

MTI

-0.71

 retira

-0.70

bė

-0.67

enscha

-0.67

рована

-0.66

ToEnd

-0.66

乳

-0.66

Jah

-0.65

 bifurcation

-0.65

POSITIVE LOGITS

tio

1.00

tc

0.91

 term

0.87

fcntl

0.86

TCS

0.84

 velocità

0.79

vmin

0.79

tc

0.79

0.77

ignal

0.76

Activations Density 0.026%

No Known Activations