© 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. 58503
    Prev
    Next
    INDEX
    Explanations

    quoted phrases

    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
    dacia
    -1.77
    嫫
    -1.75
    FormUrlEncoded
    -1.71
     册
    -1.68
    Mitar
    -1.68
    atedral
    -1.65
     zwaar
    -1.63
     zowel
    -1.62
     iedere
    -1.62
     It
    -1.62
    POSITIVE LOGITS
    u
    2.48
     we
    2.23
     viſ
    2.22
    ’
    2.13
    z
    2.02
     ؛
    1.97
    t
    1.97
    ،
    1.95
    A
    1.95
    ti
    1.86
    Activations Density 0.008%

    No Known Activations