© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    anymore, than, E, immutable

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

    The neuron activates on numeric tokens containing decimal points (i.e. floating-point numbers).

    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
    在我
    0.75
     season
    0.72
    ៃ
    0.71
    uesday
    0.71
     настроение
    0.68
    ollipop
    0.66
    节目
    0.66
    క్కడ
    0.66
     happenings
    0.66
     желание
    0.65
    POSITIVE LOGITS
     (−
    0.77
     (${
    0.70
     Xiong
    0.69
     terdiri
    0.68
     Gegensatz
    0.66
     Implicit
    0.66
    而成
    0.66
     ಅಥವಾ
    0.65
     yalnızca
    0.65
     Somit
    0.65
    Activations Density 0.001%

    No Known Activations