© 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. 57371
    Prev
    Next
    INDEX
    Explanations

    status bar or bottom bar

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

    This neuron detects mentions of user‐interface icons (the word “icon” and its surrounding context).

    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
     jeff
    -0.84
     răm
    -0.81
     žen
    -0.79
    arki
    -0.78
    ▲
    -0.75
    按钮
    -0.73
    luğu
    -0.73
    thigh
    -0.72
    otum
    -0.71
     creș
    -0.71
    POSITIVE LOGITS
     status
    2.19
    status
    1.91
     Status
    1.87
    StatusBar
    1.76
    Status
    1.69
    STATUS
    1.63
     стату
    1.45
    statusBar
    1.39
    setStatus
    1.36
     статус
    1.30
    Activations Density 0.011%

    No Known Activations