© 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. 120115
    Prev
    Next
    INDEX
    Explanations

    html attribute names

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

    HTML/XML attribute assignments, specifically the pattern `attribute="value"` in markup code.

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

    The neuron detects HTML tags’ inline style attributes (i.e. occurrences of `style="…"`).

    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
    ’
    -2.19
     
    -2.14
    _
    -2.08
    なども
    -1.89
     \
    -1.75
     because
    -1.75
    \
    -1.75
     teamed
    -1.71
     also
    -1.67
     for
    -1.61
    POSITIVE LOGITS
     the
    1.88
     anún
    1.70
    腟
    1.66
     camiset
    1.63
     maravill
    1.59
    8
    1.59
     ترجمه
    1.57
    吅
    1.55
    .
    1.54
    ⽼
    1.54
    Activations Density 0.015%

    No Known Activations