© 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. 40019
    Prev
    Next
    INDEX
    Explanations

    programming boolean variables

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

    This neuron detects occurrences of the C-style boolean type keyword (bool) in code.

    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
     Either
    -1.39
     Both
    -1.34
     both
    -1.34
     their
    -1.30
     either
    -1.29
     sowohl
    -1.28
     there
    -1.27
    ∓
    -1.26
     दोनों
    -1.24
     Reſ
    -1.21
    POSITIVE LOGITS
    genheiten
    1.73
    6
    1.70
    cznej
    1.56
    8
    1.53
    2
    1.52
    готовление
    1.45
    9
    1.45
    peka
    1.43
    on
    1.38
    `)
    1.38
    Activations Density 0.045%

    No Known Activations