© 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. 179161
    Prev
    Next
    INDEX
    Explanations

    events and planning

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

    account name authentication care

    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
     哦
    0.54
     separar
    0.50
     introns
    0.49
     symbol
    0.48
     薄
    0.48
     代
    0.48
     চিত
    0.48
     オ
    0.47
     嗯
    0.47
     économ
    0.47
    POSITIVE LOGITS
    форм
    0.50
    require
    0.48
    weekly
    0.46
    these
    0.46
     estrange
    0.45
    the
    0.45
    directions
    0.45
    движи
    0.45
    rlen
    0.44
    opportunities
    0.44
    Activations Density 0.001%

    No Known Activations