© 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. 105487
    Prev
    Next
    INDEX
    Explanations

    CSS selectors and properties

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

    CSS selectors and jQuery/JavaScript code targeting DOM elements by class or ID with chaining methods.

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

    This neuron detects HTML element names and positional pseudo‐selectors (e.g. tag names like tr, td, table combined with constructs like “:eq(…)”) within CSS or jQuery selection chains.

    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
     if
    -2.34
     for
    -2.20
     in
    -2.06
     by
    -2.05
     on
    -1.90
     any
    -1.80
     at
    -1.77
     all
    -1.77
    1
    -1.77
     even
    -1.74
    POSITIVE LOGITS
    已經
    1.62
     distintas
    1.56
    pulseira
    1.53
    Ꮒ
    1.52
     trám
    1.47
     olika
    1.46
     ráp
    1.46
     kteří
    1.45
    が無い
    1.41
     reparación
    1.41
    Activations Density 0.035%

    No Known Activations