© 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. 128639
    Prev
    Next
    INDEX
    Explanations

    jQuery usage

    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
    n
    -2.13
     ”
    -1.89
    ne
    -1.89
    c
    -1.79
     Then
    -1.77
    en
    -1.74
    d
    -1.73
    le
    -1.70
    ↵↵↵
    -1.70
    ,”
    -1.69
    POSITIVE LOGITS
     senderos
    1.92
    Couleur
    1.81
    余談
    1.70
    playera
    1.69
    jaqueta
    1.60
    gucig
    1.59
    脚步
    1.58
     аккура
    1.57
    是没有
    1.56
    我来
    1.55
    Activations Density 0.010%

    No Known Activations