© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71934
    Prev
    Next
    INDEX
    Explanations

    html input type declaration

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

    The neuron fires on HTML attribute tokens—especially the “type” attribute in input elements.

    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
    ↵
    -2.98
    [
    -2.17
    about
    -2.06
    ‘
    -2.05
     ‘‘
    -2.03
    …”
    -1.95
    *
    -1.92
    who
    -1.91
    E
    -1.83
    ‘‘
    -1.80
    POSITIVE LOGITS
     of
    2.48
    endforeach
    1.88
     Also
    1.87
     пришла
    1.78
    玨
    1.73
     conversar
    1.68
     zakon
    1.63
    bermuda
    1.62
     greateſt
    1.60
     sposob
    1.59
    Activations Density 0.020%

    No Known Activations