© 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. 10-GEMMASCOPE-RES-131K
    7. 45744
    Prev
    Next
    INDEX
    Explanations

    html, css, ui elements

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

    This neuron fires on HTML tag openings—especially when a tag carries a class attribute (e.g. “<nav class=…>”, “<div class=…>”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    providedIn
    -1.50
     andere
    -1.39
    ële
    -1.31
    ,
    -1.30
     '
    -1.27
    「
    -1.22
     
    -1.22
    下雨
    -1.21
     други
    -1.19
     anderen
    -1.17
    POSITIVE LOGITS
     debería
    1.49
     conster
    1.48
     treball
    1.41
     conforto
    1.41
    ecé
    1.41
     alimente
    1.36
     nativa
    1.35
    あが
    1.34
    が使
    1.30
     Pristup
    1.30
    Activations Density 0.133%

    No Known Activations