© 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. 22-GEMMASCOPE-RES-131K
    7. 68985
    Prev
    Next
    INDEX
    Explanations

    xsi namespace declarations

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

    The neuron detects XML Schema Instance namespace declarations (i.e. the “xsi:” prefix and related schema‐attribute names).

    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
     étanche
    -1.25
     également
    -1.15
    久し
    -1.12
    también
    -1.11
    あー
    -1.10
     også
    -1.09
    ほんと
    -1.09
     nœ
    -1.09
    筈
    -1.08
     también
    -1.06
    POSITIVE LOGITS
     as
    1.45
     when
    1.40
     may
    1.38
     during
    1.28
     for
    1.26
     in
    1.25
     at
    1.22
     took
    1.16
     just
    1.16
     actually
    1.14
    Activations Density 0.037%

    No Known Activations