© 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. 34-GEMMASCOPE-RES-131K
    4. 294
    Prev
    Next
    INDEX
    Explanations

    program exit or wait status

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

    The neuron detects C/C++ preprocessor include directives by strongly activating on header‐file tokens (e.g. the parts of “#include <sys/wait.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_34/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
    лива
    -0.72
    SSC
    -0.71
     tấn
    -0.71
    тный
    -0.69
    ueur
    -0.69
    LG
    -0.69
     Sable
    -0.69
     Gie
    -0.69
     awn
    -0.69
     fattori
    -0.68
    POSITIVE LOGITS
     exit
    1.76
     Exit
    1.55
     wait
    1.55
     exited
    1.49
    Exit
    1.44
    wait
    1.42
    exit
    1.41
    Exited
    1.29
     Wait
    1.23
    Wait
    1.22
    Activations Density 0.026%

    No Known Activations