© 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. 10980
    Prev
    Next
    INDEX
    Explanations

    main function signature

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

    The neuron fires on code entry‐point declarations, especially occurrences of “main” (e.g. int main(), public static void main, 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_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
     its
    -1.05
     různých
    -1.04
     otorg
    -1.00
     pudieron
    -0.99
     juzg
    -0.98
     aislado
    -0.96
    抱怨
    -0.95
     luoghi
    -0.93
    に入れる
    -0.91
     različ
    -0.91
    POSITIVE LOGITS
     <",
    1.23
     Veh
    1.13
     indisponible
    1.12
    склад
    1.12
    　　　　　　　　
    1.10
    。　　
    1.08
    　　　　　　
    1.07
     mondi
    1.07
    карта
    1.06
     kyt
    1.05
    Activations Density 0.013%

    No Known Activations