© 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. 10-GEMMASCOPE-RES-131K
    7. 73632
    Prev
    Next
    INDEX
    Explanations

    JavaScript code

    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_10/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
     It
    -2.33
     This
    -1.92
     There
    -1.80
     ragazza
    -1.56
     Either
    -1.55
     The
    -1.48
     Another
    -1.47
     Ubicación
    -1.46
     Its
    -1.46
     zarówno
    -1.45
    POSITIVE LOGITS
     若い
    1.73
    ificação
    1.72
     娘
    1.59
    äiv
    1.58
     today
    1.58
    ing
    1.48
    یا
    1.47
     atau
    1.46
    er
    1.45
    機會
    1.45
    Activations Density 0.003%

    No Known Activations