© 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. 34-GEMMASCOPE-RES-131K
    7. 30352
    Prev
    Next
    INDEX
    Explanations

    window events and properties

    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
    уна
    -0.77
    acti
    -0.76
    Kra
    -0.75
     fighting
    -0.74
    銹
    -0.71
     Duluth
    -0.71
     profesora
    -0.69
    coop
    -0.69
    Enclosure
    -0.69
    修炼
    -0.68
    POSITIVE LOGITS
     window
    2.09
     windows
    1.89
    window
    1.87
     Window
    1.68
    Window
    1.57
     WINDOW
    1.38
     Windows
    1.27
    windows
    1.23
    窓
    1.22
    窗口
    1.19
    Activations Density 0.014%

    No Known Activations