© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71564
    Prev
    Next
    INDEX
    Explanations

    code delimiters and programming keywords

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

    The neuron fires on programming identifiers or property names (e.g. CamelCase or snake_case tokens) rather than ordinary words.

    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
     perak
    -1.75
     Ministre
    -1.70
     paille
    -1.67
     tanam
    -1.63
     kedi
    -1.57
     norvég
    -1.55
     kitab
    -1.55
     viande
    -1.55
     boisson
    -1.54
     transparan
    -1.50
    POSITIVE LOGITS
     It
    1.93
     ebenfalls
    1.59
     now
    1.51
     sempre
    1.50
    ά
    1.45
     same
    1.45
     tiež
    1.42
     Each
    1.40
     since
    1.39
     if
    1.38
    Activations Density 0.060%

    No Known Activations