© 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. 84812
    Prev
    Next
    INDEX
    Explanations

    purpose of

    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
     ujar
    -1.84
    ありました
    -1.73
     trouva
    -1.68
    毟
    -1.63
    产生了
    -1.60
     motocicletas
    -1.59
     maravill
    -1.59
     実例
    -1.57
     acondicion
    -1.56
    ῖν
    -1.55
    POSITIVE LOGITS
    0
    2.06
    (
    2.05
    d
    1.99
    on
    1.81
    [
    1.78
    %
    1.73
    4
    1.69
    (\
    1.68
    {\
    1.66
    =
    1.66
    Activations Density 0.013%

    No Known Activations