© 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. 131004
    Prev
    Next
    INDEX
    Explanations

    ifdef preprocessor directive

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

    The neuron activates on numeric literals that appear in preprocessor directives (e.g. the numbers after #ifdef, #ifndef, #undef, defined, etc.).

    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
     "
    -2.88
    <em>
    -2.30
     
    -2.17
     Prinzip
    -2.16
     did
    -2.05
    图为
    -2.05
     \
    -1.99
     [
    -1.99
     «
    -1.98
     agradable
    -1.95
    POSITIVE LOGITS
     menyen
    3.20
     perak
    2.86
     istan
    2.77
    栊
    2.73
     alip
    2.73
     diki
    2.70
     rajut
    2.67
     Teknik
    2.67
     restoran
    2.64
     hina
    2.63
    Activations Density 0.008%

    No Known Activations