© 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. 62855
    Prev
    Next
    INDEX
    Explanations

    code, links, and labels

    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
    奥运
    -0.86
    谈判
    -0.75
     продаже
    -0.74
    放过
    -0.73
    ][]
    -0.73
     çiçek
    -0.73
    tiefel
    -0.73
     {};
    -0.73
     
    -0.72
     glyphicon
    -0.71
    POSITIVE LOGITS
     yours
    0.78
     Helpful
    0.75
    derabad
    0.72
    minente
    0.70
     magnetite
    0.69
    SONS
    0.69
    绪
    0.69
     rangers
    0.68
    urma
    0.68
    zey
    0.68
    Activations Density 0.016%

    No Known Activations