© 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. 22-GEMMASCOPE-RES-131K
    7. 67940
    Prev
    Next
    INDEX
    Explanations

    javascript code endings

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

    This neuron consistently fires on jQuery call syntax—especially the “$(…)” selector/chain and the accompanying “});” that closes event‐handler definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     COOKIE
    -1.14
     kaos
    -1.11
     to
    -1.11
     saks
    -1.11
     göm
    -1.08
     karbon
    -1.05
     that
    -1.02
     katk
    -1.02
     kuv
    -1.00
     teka
    -1.00
    POSITIVE LOGITS
    udessa
    0.92
     хотел
    0.90
    早上
    0.89
    aliyun
    0.88
    3
    0.86
    渕
    0.86
    On
    0.86
    ='\
    0.85
     zmian
    0.85
    manteau
    0.85
    Activations Density 0.002%

    No Known Activations