© 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. 77876
    Prev
    Next
    INDEX
    Explanations

    ERROR]

    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
    菖
    -0.77
    っぽい
    -0.77
    стюм
    -0.77
     parall
    -0.74
    رده
    -0.74
     Pé
    -0.74
     usine
    -0.73
    ppie
    -0.73
     Crate
    -0.72
     YU
    -0.72
    POSITIVE LOGITS
    떤
    0.89
    <0xE7>
    0.85
     szczę
    0.79
    endaftar
    0.78
    usione
    0.77
    去世
    0.77
    tokenId
    0.75
    肯定
    0.75
    shund
    0.75
     {[
    0.73
    Activations Density 0.001%

    No Known Activations