© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84146
    Prev
    Next
    INDEX
    Explanations

    mouse button down events

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

    The neuron activates on programming event‐ or action‐name tokens in code (e.g. case labels like “ACTION_DOWN” or handler names like “onKeyUp,” “KeyDown,” etc.).

    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
     RBIs
    -0.88
     Tib
    -0.72
    ayet
    -0.71
    matern
    -0.70
     rendezvous
    -0.70
    gola
    -0.70
    OTING
    -0.69
    weeks
    -0.69
    Monday
    -0.68
    Hang
    -0.68
    POSITIVE LOGITS
     down
    2.59
    down
    1.99
    Down
    1.91
    DOWN
    1.77
     Down
    1.76
     DOWN
    1.65
    sedown
    1.46
    ダウン
    1.41
    mousedown
    1.39
    MouseDown
    1.34
    Activations Density 0.038%

    No Known Activations