© 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. 76936
    Prev
    Next
    INDEX
    Explanations

    xml document tags

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

    The neuron fires on the “</” token sequence that begins XML/HTML closing 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
    どうも
    -0.93
    前言
    -0.87
    ulasi
    -0.83
     ballons
    -0.83
    monter
    -0.80
     ícone
    -0.75
     “...
    -0.75
     Stretcher
    -0.74
    失礼
    -0.73
     وآ
    -0.72
    POSITIVE LOGITS
    param
    1.24
     param
    1.09
     nooit
    0.93
     nao
    0.92
    "./
    0.90
     Pascal
    0.88
     escenarios
    0.87
     tchèque
    0.87
     poliéster
    0.86
    summary
    0.84
    Activations Density 0.003%

    No Known Activations