© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64990
    Prev
    Next
    INDEX
    Explanations

    free software files

    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
     الجد
    -0.75
    rani
    -0.73
     arterio
    -0.69
     RUN
    -0.69
     vitesse
    -0.68
     Lister
    -0.68
    ூ
    -0.67
     Patt
    -0.66
    fani
    -0.65
    RUN
    -0.65
    POSITIVE LOGITS
     science
    0.70
    巒
    0.69
    kont
    0.69
     Forschung
    0.68
     widening
    0.66
    mks
    0.65
    avares
    0.65
     phan
    0.65
    ğı
    0.65
    cairo
    0.65
    Activations Density 0.056%

    No Known Activations