© 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. 10-GEMMASCOPE-RES-131K
    7. 128822
    Prev
    Next
    INDEX
    Explanations

    path expressions

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

    This neuron activates on XPath/XML path‐query operators (slashes, double slashes, brackets) and related tokens that structure XPath expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    1
    -1.66
    alanta
    -1.47
    uire
    -1.38
     vuitton
    -1.35
     even
    -1.34
    herit
    -1.34
    ciutto
    -1.33
     importance
    -1.30
     =
    -1.30
    itivo
    -1.27
    POSITIVE LOGITS
     Ähnliche
    1.64
    damen
    1.59
     Daß
    1.57
     proposé
    1.55
    Приготовление
    1.54
    全世界
    1.52
     praça
    1.51
     rústica
    1.50
    ستارهای
    1.48
    कडाउन
    1.48
    Activations Density 0.004%

    No Known Activations