© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111610
    Prev
    Next
    INDEX
    Explanations

    programming function calls

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

    references to files or methods in programming code, particularly in stack traces and file paths.

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

    This neuron detects programming-language or assembly keywords that indicate function or method calls/invocations.

    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
     нашей
    -1.59
    Những
    -1.59
    힣
    -1.56
     trám
    -1.55
    ,"
    -1.53
    Sự
    -1.52
     необходимые
    -1.47
     travailleurs
    -1.42
     эти
    -1.41
     maquinaria
    -1.41
    POSITIVE LOGITS
     this
    1.72
     tanda
    1.71
     icona
    1.55
    𒊹
    1.51
     nech
    1.50
     Since
    1.48
    ()]);
    1.44
    ICOLON
    1.43
    []]
    1.42
    '],
    
    1.40
    Activations Density 0.003%

    No Known Activations