© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    c++ constructors and class definitions

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

    This neuron fires on C++ (and similar) scope‐resolution/namespace qualifiers (the “::” operator in fully qualified names).

    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
     snow
    0.73
    ;
    0.73
     fad
    0.73
     so
    0.71
     snowball
    0.71
     gee
    0.69
     couples
    0.69
    <0x80>
    0.68
    so
    0.68
     Couples
    0.68
    POSITIVE LOGITS
    詹
    0.86
     utilizzo
    0.82
    entrada
    0.80
    дія
    0.80
     inizia
    0.79
    interno
    0.79
     Tuttavia
    0.79
     Володимир
    0.79
    Categorie
    0.77
    puede
    0.77
    Activations Density 0.003%

    No Known Activations