© 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. 31182
    Prev
    Next
    INDEX
    Explanations

    border colors and styles

    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
    unya
    -0.88
    rección
    -0.78
    resume
    -0.75
    enschap
    -0.75
    男友
    -0.72
     handbook
    -0.71
    фера
    -0.71
     compos
    -0.71
    落ち
    -0.70
    습니다
    -0.70
    POSITIVE LOGITS
     gains
    0.94
     Gains
    0.85
    🌷
    0.77
    Contacts
    0.75
    gains
    0.73
     obiet
    0.73
    gac
    0.73
    🌺
    0.69
     Navajo
    0.69
    besar
    0.69
    Activations Density 0.054%

    No Known Activations