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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93429
    Prev
    Next
    INDEX
    Explanations

    xml/html/plist tags

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

    The neuron is detecting XML/HTML markup syntax, especially attribute‐assignment sequences like =″…″, XML declarations, and tag delimiters.

    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
     Function
    -0.80
    猿
    -0.73
     sel
    -0.73
    function
    -0.73
    WORD
    -0.71
     Doppel
    -0.71
    }<\
    -0.69
    ->__
    -0.69
     function
    -0.68
    ługa
    -0.68
    POSITIVE LOGITS
    dang
    0.88
    캠
    0.81
     několik
    0.80
    обще
    0.77
    иму
    0.77
    iare
    0.76
     observance
    0.75
    тельств
    0.73
    пыта
    0.73
     gereken
    0.73
    Activations Density 0.012%

    No Known Activations