© 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. 34-GEMMASCOPE-RES-131K
    7. 47349
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags

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

    The neuron is specialized to pick out HTML `<meta>` tag elements and their attribute/value tokens (e.g. the http-equiv, charset, viewport, X-UA-Compatible, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Sem
    -0.74
    routed
    -0.73
    signal
    -0.71
    rå
    -0.67
     nichts
    -0.67
     signal
    -0.67
     Chim
    -0.67
    VertexAttrib
    -0.66
    ják
    -0.65
    FlowLayout
    -0.65
    POSITIVE LOGITS
    headless
    0.77
    بط
    0.72
    mnar
    0.71
     Schumacher
    0.69
    lungs
    0.69
    OCR
    0.69
    //'
    0.69
    saveButton
    0.67
    حث
    0.67
    taan
    0.66
    Activations Density 0.044%

    No Known Activations