© 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. 7605
    Prev
    Next
    INDEX
    Explanations

    spills and leakages

    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
    >
    -2.09
    {
    -2.09
    ين
    -1.95
    廰
    -1.87
     wha
    -1.83
     farmacia
    -1.71
    ль
    -1.69
     exacting
    -1.67
     Memoriam
    -1.67
    グラフ
    -1.66
    POSITIVE LOGITS
    u
    2.03
    ранее
    1.93
     spill
    1.88
     Verfasser
    1.87
    艿
    1.84
    <td>
    1.82
    入って
    1.81
    riculares
    1.81
     unſ
    1.80
     spills
    1.79
    Activations Density 0.004%

    No Known Activations