© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    variable assignment or equality

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

    The neuron predominantly fires on numeric values (constants or measurements) in technical/math contexts.

    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
    ([^
    0.68
    ($"{
    0.68
     ((
    0.66
    (`${
    0.66
     (;
    0.65
     যিনি
    0.59
    (((
    0.58
     মাননীয়
    0.58
    第一时间
    0.58
     (*
    0.57
    POSITIVE LOGITS
    ≒
    0.69
    =-\
    0.62
    ＝
    0.61
    ≳
    0.61
    ≥
    0.61
     ≥
    0.60
    =
    0.60
    =$\
    0.59
     н
    0.58
     مۇ
    0.57
    Activations Density 0.001%

    No Known Activations