© 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-3-27B-IT · 31-GEMMASCOPE-2-RES-65K · 4200 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-65K
4200

INDEX

Explanations

`.py` or programming languages

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_31_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

Not in Any Lists

No Comments

Negative Logits

𝖆

0.35

茘

0.34

ECTION

0.33

하고자

0.33

managerpage

0.32

𝔪

0.32

nahi

0.31

мести

0.31

ма

0.31

 чле

0.30

POSITIVE LOGITS

0.38

 zowel

0.37

 increases

0.35

0.34

0.34

 Audio

0.33

 både

0.33

 Pine

0.33

 Hyper

0.32

 Size

0.32

Activations Density 0.394%

No Known Activations