© 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. 10-GEMMASCOPE-RES-131K
    7. 85245
    Prev
    Next
    INDEX
    Explanations

    mouse events and data types

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

    The neuron activates on references to programming “Event” classes (e.g. MouseEvent, MotionEvent).

    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
    At
    -3.00
    N
    -2.94
    after
    -2.89
    As
    -2.86
    𖣘
    -2.59
    Not
    -2.50
    To
    -2.50
    Just
    -2.48
    」
    -2.47
    No
    -2.45
    POSITIVE LOGITS
    
    3.16
    鬭
    2.69
     แต่
    2.63
    阇
    2.52
    邶
    2.47
    
    2.42
     hunne
    2.42
    
    2.41
     solches
    2.38
    珰
    2.34
    Activations Density 0.000%

    No Known Activations