© 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. 10298
    Prev
    Next
    INDEX
    Explanations

    jQuery

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

    the word "jQuery" (and its variants like "Jquery" or "jquery").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the term “jQuery” (and its shorthand “$”) in code or text.

    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
    a
    -2.63
     This
    -2.47
     这个
    -2.13
     Now
    -2.11
     That
    -2.11
    p
    -2.09
    ldots
    -2.00
     '
    -1.99
    is
    -1.98
     have
    -1.98
    POSITIVE LOGITS
    他们是
    2.05
    摇了
    2.03
    他会
    1.99
     belangrijk
    1.92
    peicher
    1.91
    他没有
    1.89
     creía
    1.88
    傕
    1.88
    回来的
    1.84
     actief
    1.82
    Activations Density 0.031%

    No Known Activations