© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7343
    Prev
    Next
    INDEX
    Explanations

    CSS selectors and DOM manipulation

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

    The neuron strongly responds to mentions of JavaScript library filenames or URLs (i.e. tokens forming “*.js” paths and library names like jQuery, migrate, require.js, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    险
    0.64
    HTML
    0.57
    วิว
    0.56
    沉
    0.54
    classlist
    0.54
     HTML
    0.54
    innerHTML
    0.53
    父
    0.53
    parentElement
    0.53
    postcss
    0.53
    POSITIVE LOGITS
     jq
    0.74
     dataType
    0.71
    dataType
    0.67
    DataType
    0.62
     przed
    0.60
    nq
    0.57
     datatype
    0.57
     Tukey
    0.55
     peritoneum
    0.54
     Dearborn
    0.54
    Activations Density 0.009%

    No Known Activations