© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8962
    Prev
    Next
    INDEX
    Explanations

    git clone, code, debug, compiler

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

    The neuron flags mentions of version‐control concepts and tools (e.g. “distributed,” “control,” “systems,” “Mercurial,” “Bazaar”).

    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
     ,
    0.77
    Fcn
    0.69
    Must
    0.66
    Delivery
    0.66
    c
    0.64
    =
    0.64
    Customers
    0.62
    0.62
    Freq
    0.61
    ,
    0.61
    POSITIVE LOGITS
     IntelliJ
    0.90
     Dateien
    0.79
     fichiers
    0.77
     configFile
    0.77
    gradle
    0.76
     файлов
    0.74
    Gradle
    0.73
     progetti
    0.73
     arquivos
    0.72
     Gradle
    0.71
    Activations Density 0.334%

    No Known Activations