© 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. 10-GEMMASCOPE-RES-131K
    7. 86361
    Prev
    Next
    INDEX
    Explanations

    mouse clicks and actions

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

    The neuron fires on mentions of mouse‐button events and related callback terms (e.g. “mouse,” “button,” “Down,” “Pressed,” “Clicked”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.41
     for
    -1.76
     tetapi
    -1.61
    容易
    -1.57
     in
    -1.56
     before
    -1.55
    f
    -1.55
    ’
    -1.55
     he
    -1.45
     –
    -1.45
    POSITIVE LOGITS
    獁
    1.95
    鉏
    1.89
    喁
    1.83
    ندم
    1.71
    鹟
    1.69
    
    1.67
    Ꮵ
    1.67
    骝
    1.65
     fasse
    1.63
    ⃚
    1.62
    Activations Density 0.019%

    No Known Activations