© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81145
    Prev
    Next
    INDEX
    Explanations

    XSLT transformer and XPath

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

    The neuron fires on XML/XSL markup tokens—especially the XML prolog (`<?xml…?>`), namespace declarations (`xmlns`, `xsl:`), version attributes, and related tags.

    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
     Stur
    -0.75
     актриса
    -0.69
    importation
    -0.69
    返回值
    -0.69
    針
    -0.68
     Fuck
    -0.68
    Fuck
    -0.68
    谐
    -0.68
     Sewing
    -0.67
    shafen
    -0.67
    POSITIVE LOGITS
    xsl
    1.25
    Transformer
    1.24
     Transformer
    1.13
     Saxon
    1.09
     transformer
    0.99
    transformer
    0.94
     DOM
    0.94
    Saxon
    0.93
     styles
    0.92
     XPath
    0.91
    Activations Density 0.148%

    No Known Activations