© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    `id` `pairs` `character` `array` `Url` `time`

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

    The neuron is firing on programming identifiers and symbols—names of functions, variables, constants, and similar code tokens.

    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
    erol
    0.61
     नव्या
    0.57
     অন
    0.57
    skii
    0.54
     thậm
    0.54
    స్కీ
    0.54
    쏠
    0.54
     জুড়ে
    0.54
    വിൽ
    0.54
    ErrorBoundary
    0.54
    POSITIVE LOGITS
     which
    0.89
    ;
    0.81
    which
    0.75
    ；
    0.69
    [];
    0.69
     która
    0.64
     ;
    0.63
    。「
    0.63
     które
    0.63
     vilket
    0.62
    Activations Density 0.000%

    No Known Activations