© 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. 65693
    Prev
    Next
    INDEX
    Explanations

    include unistd, CMake, CDATA, Wim

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

    This neuron detects occurrences of the C header unistd.h being included (i.e. “#include <unistd.h>”).

    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
     After
    -2.80
    These
    -2.77
    That
    -2.75
    What
    -2.75
    While
    -2.70
     Normally
    -2.67
     Many
    -2.67
    This
    -2.66
    During
    -2.64
     the
    -2.59
    POSITIVE LOGITS
     男人
    3.09
    憷
    2.81
    廰
    2.66
     wahre
    2.55
     使っ
    2.47
    蕷
    2.45
     einzigartige
    2.41
    姌
    2.39
     insanlar
    2.38
    銠
    2.38
    Activations Density 0.015%

    No Known Activations