© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60599
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    栳
    -2.53
    of
    -2.17
    .
    -2.05
     laquelle
    -1.86
    -1.72
    関する
    -1.68
    ſſel
    -1.63
     appelée
    -1.61
    celular
    -1.61
    your
    -1.61
    POSITIVE LOGITS
     jPanel
    2.13
    にほんブログ村
    2.11
    澂
    2.09
    翆
    2.09
    おはよう
    2.03
    ։
    2.03
     an
    1.98
    ではでは
    1.95
    uerung
    1.92
    呜呜
    1.91
    Activations Density 0.023%

    No Known Activations