© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15670
    Prev
    Next
    INDEX
    Explanations

    preface, chapter, introduction

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

    Table of contents, outline, abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astly
    0.43
    ischen
    0.41
     Hansen
    0.40
    ©
    0.39
    arks
    0.39
    uan
    0.39
    antes
    0.38
    bö
    0.38
    oreau
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
    POSITIVE LOGITS
    Preface
    0.47
     conceal
    0.46
     diligence
    0.45
    壹章
    0.43
     determinate
    0.42
     修改
    0.42
    蓋
    0.42
     Preface
    0.41
    渽
    0.41
     preface
    0.40
    Activations Density 0.020%

    No Known Activations