© 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. 34-GEMMASCOPE-RES-131K
    7. 76617
    Prev
    Next
    INDEX
    Explanations

    JavaScript closing parentheses and braces

    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_34/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
     such
    -1.01
     tungkol
    -0.83
    fastjson
    -0.81
     Infatti
    -0.77
     enfin
    -0.75
    ˆ
    -0.73
    勐
    -0.72
     صباح
    -0.72
     astfel
    -0.72
     така
    -0.72
    POSITIVE LOGITS
    console
    1.39
     console
    1.27
    alert
    1.25
    var
    1.10
     return
    1.08
    return
    1.08
    void
    1.05
    window
    1.05
    parseFloat
    1.01
     alert
    1.00
    Activations Density 0.007%

    No Known Activations