© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6250
    Prev
    Next
    INDEX
    Explanations

    function and type declarations

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

    The neuron responds to programming-style tokens—function names, API calls, underscores, and other code identifiers.

    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_31_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
    Ultra
    0.67
     metais
    0.66
    =>{
    0.65
     ->
    0.63
    ->
    0.62
    >{{
    0.59
     Ultra
    0.57
    ({{
    0.57
    ultra
    0.57
    ->"
    0.57
    POSITIVE LOGITS
     &$
    0.70
     :\
    0.70
     $:
    0.69
    .\
    0.63
    ):\
    0.62
    ?\
    0.61
    &\
    0.61
     &\
    0.61
    就行
    0.58
     reconstructing
    0.57
    Activations Density 0.000%

    No Known Activations