© 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. 59980
    Prev
    Next
    INDEX
    Explanations

    document structure tags

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

    This neuron detects markup delimiters and tag names (e.g., XML/HTML-like angle-bracketed 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
     echt
    -0.82
    Xk
    -0.80
    wała
    -0.76
    unakan
    -0.74
    Supplement
    -0.74
    eeqa
    -0.73
     lawan
    -0.70
    ⎨
    -0.69
    )+"
    -0.69
    Subviews
    -0.69
    POSITIVE LOGITS
    phyr
    0.88
     encoding
    0.81
    FORM
    0.81
    idez
    0.80
    폼
    0.77
    ύν
    0.75
     supernova
    0.75
    tov
    0.75
    औ
    0.74
    kov
    0.74
    Activations Density 0.001%

    No Known Activations