© 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. 10-GEMMASCOPE-RES-131K
    4. 104081
    Prev
    Next
    INDEX
    Explanations

    build configuration project coordinates

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

    XML tags and syntax elements in Maven POM files and configuration documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects XML namespace declarations (especially the Maven POM xmlns URI and version 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_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
     चीज़
    -1.52
    iarkan
    -1.45
    饌
    -1.37
     hábit
    -1.37
    Sziasztok
    -1.31
     tampoco
    -1.30
    LLocation
    -1.30
     we
    -1.29
     lutego
    -1.27
    дельник
    -1.27
    POSITIVE LOGITS
    ־ה
    1.76
    וּ
    1.52
    обще
    1.41
    ֶּ
    1.39
    neous
    1.26
    беріга
    1.25
    üyü
    1.24
    bakter
    1.23
    стойчи
    1.21
     война
    1.20
    Activations Density 0.165%

    No Known Activations