© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99468
    Prev
    Next
    INDEX
    Explanations

    code syntax elements following words

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

    The neuron specifically detects XPath path expressions (e.g. the leading “//”, element names, dots, and bracketed predicates).

    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
     a
    -0.88
    UIImageView
    -0.83
    ỗ
    -0.81
     illustrates
    -0.80
     told
    -0.74
     legend
    -0.74
    navigationItem
    -0.73
     entfernt
    -0.73
    lective
    -0.73
    target
    -0.72
    POSITIVE LOGITS
    [@
    1.72
    [
    1.66
    ()[
    1.47
    [(
    1.22
    )[
    1.20
    '][
    1.15
    }[
    1.09
    "][
    1.09
     [
    1.05
     [@
    1.05
    Activations Density 0.008%

    No Known Activations