© 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. 22-GEMMASCOPE-RES-131K
    7. 75187
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

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

    This neuron fires on capitalized identifiers—API calls, class or framework names, and other CamelCase code tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵↵
    -1.25
     I
    -1.23
    opie
    -1.00
     gravidez
    -0.98
    </h3>
    -0.98
     lixo
    -0.96
     juntamente
    -0.96
     they
    -0.95
     ''
    -0.93
    gewiesen
    -0.93
    POSITIVE LOGITS
     of
    2.80
     nameof
    1.30
     emblema
    1.18
     rurale
    1.13
     Suara
    1.11
     ramah
    1.10
     silueta
    1.09
     Fakta
    1.09
    вом
    1.04
    endish
    1.04
    Activations Density 0.019%

    No Known Activations