© 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. 71535
    Prev
    Next
    INDEX
    Explanations

    Kobe \| Copa \| Tijuana \| discus

    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
    U
    -3.88
    H
    -3.70
    M
    -3.69
    N
    -3.61
    </td>
    -3.48
    ?
    -3.41
    T
    -3.39
    F
    -3.38
    K
    -3.38
    D
    -3.27
    POSITIVE LOGITS
    ݮ
    2.66
     باسلام
    2.64
    噥
    2.61
    溌
    2.55
    噠
    2.53
    瓛
    2.53
    Bahan
    2.52
    ㈰
    2.48
    ⩤
    2.42
    Krankheitsbild
    2.41
    Activations Density 0.023%

    No Known Activations