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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221517
    Prev
    Next
    INDEX
    Explanations

    conversations that

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

    SMPC, Neutral, throat, Jasper

    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_262k_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
    h
    0.54
    d
    0.48
    Crawler
    0.46
    ーカー
    0.45
    Screen
    0.45
    line
    0.44
    Cities
    0.44
    ਧ
    0.44
    我不
    0.43
    period
    0.42
    POSITIVE LOGITS
     \%)$
    0.50
     ustaw
    0.50
     항
    0.50
     linkCell
    0.49
     stylu
    0.49
     ঔষধ
    0.48
    rı
    0.47
    тні
    0.47
     സംവിധ
    0.46
     Mannschaft
    0.46
    Activations Density 0.000%

    No Known Activations