© 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. 10958
    Prev
    Next
    INDEX
    Explanations

    automatic alignment and extraction

    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
    to
    -1.93
    k
    -1.75
    B
    -1.72
     variés
    -1.71
    m
    -1.69
    {
    -1.66
    V
    -1.60
     clunky
    -1.58
    最后由
    -1.55
    even
    -1.52
    POSITIVE LOGITS
     have
    2.45
     you
    1.81
     become
    1.80
    薆
    1.80
    .
    1.66
     and
    1.66
    ཋ
    1.63
     ($("#
    1.62
     see
    1.60
     which
    1.58
    Activations Density 0.022%

    No Known Activations