© 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. 4276
    Prev
    Next
    INDEX
    Explanations

    XML document parsing

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

    The neuron is a detector for the literal substring “xml,” i.e. references to XML in code or markup.

    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
    umbled
    -0.84
    的面
    -0.81
     deco
    -0.81
    それでも
    -0.81
    empl
    -0.77
     multiplex
    -0.75
    LAH
    -0.74
     gypsy
    -0.74
    Joined
    -0.73
    一個人
    -0.73
    POSITIVE LOGITS
    комо
    0.86
    POSAL
    0.81
    zerland
    0.79
    бие
    0.78
    anță
    0.78
     parseFrom
    0.77
    クサ
    0.75
    ով
    0.75
     sejarah
    0.74
     starten
    0.73
    Activations Density 0.042%

    No Known Activations