© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49184
    Prev
    Next
    INDEX
    Explanations

    xml namespaces and citations

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

    The neuron detects XML/HTML markup tokens—especially namespace declarations like “xmlns” and related tag syntax.

    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
    监管
    -0.82
     simpat
    -0.81
     incrust
    -0.80
     palma
    -0.76
     frescos
    -0.75
    Bewertung
    -0.75
     colar
    -0.73
    色は
    -0.73
     pneu
    -0.73
     solutions
    -0.73
    POSITIVE LOGITS
    ข
    0.93
    fungsi
    0.88
    ască
    0.86
    ,:,
    0.77
    Volleyball
    0.75
     Hour
    0.75
    UpdateCommand
    0.73
    рый
    0.73
    onha
    0.73
     Exemption
    0.72
    Activations Density 0.003%

    No Known Activations