© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128241
    Prev
    Next
    INDEX
    Explanations

    key codes and modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.95
    v
    -1.86
     eighteen
    -1.80
    In
    -1.78
     sixteen
    -1.77
    To
    -1.75
     nineteen
    -1.66
    d
    -1.63
     eighty
    -1.63
    ’,
    -1.63
    POSITIVE LOGITS
    犼
    1.82
    眛
    1.80
     podendo
    1.77
     algumas
    1.73
    狨
    1.73
    ⽐
    1.72
     Seleccione
    1.69
     invitado
    1.65
    燹
    1.65
    años
    1.64
    Activations Density 0.003%

    No Known Activations