© 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. 84889
    Prev
    Next
    INDEX
    Explanations

    closing brackets

    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
     which
    -1.49
    {
    -1.48
    鼷
    -1.36
    not
    -1.35
     not
    -1.32
    我们是
    -1.32
    ;
    -1.30
     them
    -1.30
    Ã
    -1.24
     nuestras
    -1.23
    POSITIVE LOGITS
    ERICAN
    1.77
    atischen
    1.63
    ของ
    1.63
     bekämp
    1.59
    ⎆
    1.53
    पुर
    1.52
    และ
    1.52
    лии
    1.48
    鄲
    1.48
    neurial
    1.48
    Activations Density 0.007%

    No Known Activations