© 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. 25162
    Prev
    Next
    INDEX
    Explanations

    closing html tags

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

    This neuron detects opening HTML heading and paragraph tags (e.g., <h1>…<h5> and <p>).

    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
     in
    -1.87
     of
    -1.83
    その
    -1.58
     syk
    -1.57
    それから
    -1.48
    the
    -1.46
    </em>
    -1.40
    q
    -1.38
    p
    -1.37
    f
    -1.37
    POSITIVE LOGITS
     fiabilidad
    1.86
     mejoras
    1.78
     hermosos
    1.77
     fenó
    1.76
     garantías
    1.73
     emisiones
    1.70
     pieles
    1.68
     impresionantes
    1.66
     continúas
    1.65
     görüntüsü
    1.65
    Activations Density 0.005%

    No Known Activations