© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106411
    Prev
    Next
    INDEX
    Explanations

    focus and blur events

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

    The neuron fires on code fragments dealing with HTML form inputs and jQuery event handlers (e.g. input attributes like id/name and methods like .blur()).

    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
    avar
    -0.79
    Jenn
    -0.77
    effective
    -0.77
     RuntimeError
    -0.77
    արդ
    -0.75
     Instructors
    -0.75
     tisíc
    -0.72
    stateParams
    -0.72
    ClCompile
    -0.71
     药
    -0.71
    POSITIVE LOGITS
     blur
    2.03
    blur
    1.95
    Blur
    1.88
     Blur
    1.69
     blurred
    1.63
    onBlur
    1.63
    blurred
    1.41
     focus
    1.38
     loss
    1.37
     blurry
    1.35
    Activations Density 0.039%

    No Known Activations