© 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. 34-GEMMASCOPE-RES-131K
    7. 62821
    Prev
    Next
    INDEX
    Explanations

    icons, image files, app metadata

    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_34/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
    gás
    -0.85
     MPs
    -0.84
    bkz
    -0.83
    elyk
    -0.81
    itettura
    -0.80
     rocky
    -0.79
    TOGGLE
    -0.79
    ܥ
    -0.79
    Fernseh
    -0.79
    ریف
    -0.78
    POSITIVE LOGITS
    ticing
    0.84
    goc
    0.84
    agenda
    0.81
    kilometer
    0.80
    Jeep
    0.79
    muerzo
    0.76
    czę
    0.76
    [&
    0.75
     aig
    0.74
     jor
    0.73
    Activations Density 0.016%

    No Known Activations