© 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. 47488
    Prev
    Next
    INDEX
    Explanations

    numbers in words

    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
    muer
    -0.81
    ström
    -0.79
    震
    -0.78
    菲
    -0.77
    liv
    -0.76
    民主党
    -0.75
    Tet
    -0.75
     need
    -0.75
     perlu
    -0.72
    jeh
    -0.72
    POSITIVE LOGITS
    atile
    0.77
     bursting
    0.77
    取代
    0.73
    allo
    0.71
     יִ
    0.69
    tvguide
    0.68
    Lyrics
    0.68
    Diámetro
    0.67
    ben
    0.67
    ׳
    0.66
    Activations Density 0.031%

    No Known Activations