© 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. 63970
    Prev
    Next
    INDEX
    Explanations

    names starting with Mar

    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
    atuur
    -0.77
     précision
    -0.73
     espec
    -0.71
    palindrome
    -0.71
     Sammlung
    -0.70
    咒
    -0.69
    효
    -0.69
    енье
    -0.69
    udesta
    -0.69
    mib
    -0.68
    POSITIVE LOGITS
    hidden
    0.73
    Ƨ
    0.71
    chement
    0.71
    ゼット
    0.70
    bain
    0.69
    stars
    0.68
    luft
    0.68
    щие
    0.67
    stasy
    0.67
    咕
    0.67
    Activations Density 0.033%

    No Known Activations