© 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. 107938
    Prev
    Next
    INDEX
    Explanations

    file path parameters

    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
    ās
    -0.70
     Regulator
    -0.70
     Senate
    -0.66
     spatially
    -0.64
    カバー
    -0.64
     Burn
    -0.64
    Burn
    -0.63
    baugh
    -0.62
     multa
    -0.61
    uré
    -0.60
    POSITIVE LOGITS
     Phnom
    0.80
    getSystem
    0.75
    TResult
    0.70
    nsf
    0.69
    gotoxy
    0.69
    batik
    0.69
     IPTV
    0.68
    itesi
    0.68
     NYU
    0.68
    oration
    0.68
    Activations Density 0.099%

    No Known Activations