© 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. 30735
    Prev
    Next
    INDEX
    Explanations

    mouse events and size adjustments

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

    The neuron strongly activates on Windows message constants (e.g. tokens making up identifiers like WM_MOUSEMOVE, WM_ENTERSIZEMOVE, WM_GETRECT, LParam, EM_*), i.e. it’s looking for Win32 message names.

    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
     поведения
    -0.93
    addEventListener
    -0.84
    eventos
    -0.79
    dne
    -0.79
    Mateo
    -0.78
     собы
    -0.78
    Scu
    -0.78
    Pah
    -0.77
    mascar
    -0.77
     behandeling
    -0.77
    POSITIVE LOGITS
     size
    0.99
    size
    0.96
     Size
    0.90
     lost
    0.90
    SIZE
    0.90
    Size
    0.88
    resize
    0.85
     перед
    0.85
    char
    0.82
     Lost
    0.82
    Activations Density 0.014%

    No Known Activations