© 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-3-27B-IT · 40-GEMMASCOPE-2-RES-65K · 4523 ｜ Neuronpedia

Home
Gemma-3-27B-IT
40-GEMMASCOPE-2-RES-65K
4523

INDEX

Explanations

harmful

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

 проблемы

0.45

 problems

0.44

いや

0.43

Problems

0.42

టీఎం

0.42

 загру

0.42

}$.

0.41

is

0.41

 MediaQuery

0.41

 Problems

0.40

POSITIVE LOGITS

 Harm

0.81

harm

0.73

Harm

0.71

HAR

0.70

 harm

0.68

 harmon

0.64

 harms

0.59

harmon

0.57

 harmonization

0.57

 Harman

0.55

Activations Density 0.085%

No Known Activations