© 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. 43919
    Prev
    Next
    INDEX
    Explanations

    core file paths

    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
     a
    -2.06
     been
    -1.69
     respald
    -1.67
    푢
    -1.66
     claramente
    -1.65
     other
    -1.57
     cuz
    -1.55
     детская
    -1.53
    इटम
    -1.52
     Vertreter
    -1.51
    POSITIVE LOGITS
    V
    1.81
    K
    1.73
    Although
    1.70
    In
    1.69
    ほとんど
    1.67
    G
    1.66
    th
    1.64
    Ꮉ
    1.57
    However
    1.57
    F
    1.55
    Activations Density 0.021%

    No Known Activations