© 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. 67413
    Prev
    Next
    INDEX
    Explanations

    when and where an event is held

    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
    aarrggbb
    -1.85
     Mudah
    -1.66
    または
    -1.66
    妓
    -1.63
     当
    -1.63
     provide
    -1.60
    辱
    -1.59
    三人
    -1.57
    masing
    -1.56
    𝐭
    -1.56
    POSITIVE LOGITS
     anunció
    1.76
    这也
    1.59
    ebly
    1.56
     in
    1.56
    (
    1.55
     pensé
    1.54
    快捷
    1.51
    狁
    1.51
    身边的
    1.48
    都已经
    1.48
    Activations Density 0.032%

    No Known Activations