© 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 · 10-GEMMASCOPE-RES-131K · 96 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
96

INDEX

Explanations

take home losses

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_10/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

-2.25

 blatantly

-2.14

There

-2.13

 When

-2.03

 Despite

-2.02

 spurred

-1.99

-1.98

-1.97

 subtly

-1.95

-1.93

POSITIVE LOGITS

 semelh

2.38

淠

2.23

౮

2.11

䛗

2.11

妧

2.11

泐

2.09

 tajem

2.09

 perigo

2.06



2.06

糁

2.05

Activations Density 0.003%

No Known Activations