© 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 · 58875 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
58875

INDEX

Explanations

ant build scripts

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

 incons

-0.77

yeur

-0.76

 Calam

-0.74

 Parla

-0.73

OBJET

-0.72

 microfiber

-0.71

 Ithaca

-0.70

ɧ

-0.70

զ

-0.69

東日本

-0.69

POSITIVE LOGITS

Ant

1.08

ant

1.05

Ant

1.04

Project

0.93

 Project

0.92

getProject

0.87

 physician

0.87

 Projekt

0.80

vaj

0.80

 Израи

0.80

Activations Density 0.053%

No Known Activations