© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31164
    Prev
    Next
    INDEX
    Explanations

    XML schema locations

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

    The neuron fires on the tokens that make up XML namespace and schema URIs (e.g. the “xmlns,” “http://…,” version numbers, slashes, and dots in those declarations).

    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
    jection
    -0.85
    ｻ
    -0.80
     kuns
    -0.79
     taler
    -0.79
     бухгал
    -0.77
     Batterie
    -0.76
     blod
    -0.75
    囑
    -0.74
    intahan
    -0.74
     CHILDREN
    -0.73
    POSITIVE LOGITS
     schema
    1.15
     schemas
    1.13
     Schema
    1.08
    schema
    1.01
    Schema
    1.00
    schemas
    0.99
     схема
    0.84
    Schemas
    0.83
     Sche
    0.83
    ^{*}(
    0.82
    Activations Density 0.007%

    No Known Activations