© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75236
    Prev
    Next
    INDEX
    Explanations

    XML namespaces

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

    The neuron activates on XML namespace declarations (the “xmlns” attributes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     have
    -1.89
     provide
    -1.79
    鹋
    -1.74
    jooq
    -1.63
     ensure
    -1.62
     begin
    -1.61
     will
    -1.61
    textTheme
    -1.60
    unjungi
    -1.58
    ꪮ
    -1.57
    POSITIVE LOGITS
    ほら
    1.59
    presented
    1.57
    primarily
    1.53
     ۱۵
    1.53
    originally
    1.50
     fondamental
    1.48
     kredi
    1.47
    硨
    1.47
     hırka
    1.46
    何故
    1.45
    Activations Density 0.012%

    No Known Activations