© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    Type declarations and function definitions

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

    the keyword "int" in programming code, particularly in type declarations and variable definitions.

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

    The neuron is keyed to the programming keyword “void.”

    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
     parfü
    -2.66
     kapak
    -2.23
     parfüm
    -2.20
     myndig
    -2.11
     göm
    -1.99
     verhind
    -1.95
     menek
    -1.92
     baskılı
    -1.91
     sinyal
    -1.89
     mengumumkan
    -1.88
    POSITIVE LOGITS
     have
    2.39
    </h2>
    2.19
     will
    2.16
     Some
    2.11
     They
    2.05
     That
    2.02
     of
    2.00
     However
    1.92
     It
    1.90
     but
    1.78
    Activations Density 0.000%

    No Known Activations