© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16559
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and code configurations

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

    The neuron fires on HTML `<form>` elements and their key attributes (e.g. id, name, method) whenever a form tag and its attribute names/values appear.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     mensen
    -1.02
    ">(</
    -0.98
    qualität
    -0.97
    Kna
    -0.94
     же
    -0.94
     للمعارف
    -0.90
    ёх
    -0.90
    getColumnIndex
    -0.89
     gebaut
    -0.89
    یب
    -0.88
    POSITIVE LOGITS
    啻
    1.15
    but
    1.10
     year
    1.08
    넬
    1.01
    BUT
    0.98
     available
    0.98
     Sortiment
    0.98
    clicking
    0.98
    You
    0.96
     پد
    0.95
    Activations Density 0.008%

    No Known Activations