© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104429
    Prev
    Next
    INDEX
    Explanations

    filenames ending in .c

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

    the ".c" file extension in source code file paths and names.

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

    This neuron detects references to C source code filenames (i.e. “.c” file names in diffs/headers).

    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
    ALLENG
    -1.55
     bolsillos
    -1.52
    ALLENGES
    -1.47
    medriver
    -1.39
     suivent
    -1.39
     voient
    -1.38
    hips
    -1.38
     said
    -1.38
    anzug
    -1.34
     decorativos
    -1.34
    POSITIVE LOGITS
     by
    1.38
     וב
    1.35
     In
    1.34
    1.33
    avoid
    1.32
     معم
    1.32
    ֽ
    1.30
    ')],
    1.29
     to
    1.28
     придется
    1.27
    Activations Density 0.030%

    No Known Activations