© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    names and last names

    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
    翃
    -3.47
     the
    -3.02
     vorliegenden
    -2.92
     erwähnten
    -2.86
     vorhandenen
    -2.75
     剤
    -2.73
     Mereka
    -2.61
     Hinblick
    -2.58
     Gegensatz
    -2.56
     gesuchten
    -2.53
    POSITIVE LOGITS
    y
    2.97
    他自己
    2.73
    </h2>
    2.64
    辗
    2.30
    ⚌
    2.20
    虓
    2.19
    他要
    2.17
     geschikt
    2.14
     archaic
    2.08
    薆
    2.02
    Activations Density 0.001%

    No Known Activations