© 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. 100290
    Prev
    Next
    INDEX
    Explanations

    measurements in millimeters

    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
    幛
    -1.71
    勗
    -1.57
     vérité
    -1.52
    ゼント
    -1.50
    了两
    -1.49
    tellte
    -1.49
     alſo
    -1.49
    
    -1.48
     fulfilled
    -1.48
     igång
    -1.48
    POSITIVE LOGITS
    gemar
    1.73
    *
    1.64
     '
    1.63
     /
    1.55
     invitar
    1.54
     například
    1.53
    有不
    1.45
     adentro
    1.45
     Чтобы
    1.44
     (!)
    1.43
    Activations Density 0.013%

    No Known Activations