© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11283
    Prev
    Next
    INDEX
    Explanations

    go programming language

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

    This neuron detects Go standard‐library package declarations/import paths (e.g. “net/http”, “encoding/json”, “os/exec”) in documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lám
    0.81
     pá
    0.78
     třeba
    0.74
     dát
    0.73
    ~!
    0.72
     pár
    0.71
    ová
    0.70
    SERVICIO
    0.70
     Franti
    0.69
     antecedentes
    0.68
    POSITIVE LOGITS
     Go
    0.85
    ⼒
    0.76
    WaitGroup
    0.75
     strconv
    0.74
     Kubernetes
    0.73
    pkg
    0.73
     अंग्रे
    0.72
     Ка
    0.71
     Ки
    0.71
    logrus
    0.71
    Activations Density 0.016%

    No Known Activations