© 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. 950
    Prev
    Next
    INDEX
    Explanations

    system tray and taskbar

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on tokens naming taskbar/system‐tray UI elements (e.g. “Task,” “bar,” “Notification,” “значок,” “панели задач”). It’s looking for mentions of taskbar or notification‐icon components.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    DialogComponent
    -0.75
    čne
    -0.72
    rungen
    -0.71
     cello
    -0.71
    ウィキ
    -0.71
    pageNumber
    -0.69
    Celular
    -0.68
    핍
    -0.68
     HARRIS
    -0.68
     Harris
    -0.68
    POSITIVE LOGITS
     tray
    3.11
     Tray
    2.61
    tray
    2.52
    Tray
    2.45
     trays
    2.20
     taskbar
    2.06
     Task
    1.78
    Task
    1.77
     task
    1.63
     syst
    1.55
    Activations Density 0.044%

    No Known Activations