© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7243
    Prev
    Next
    INDEX
    Explanations

    numeric assignments

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

    The neuron fires on numeric expressions—decimal numbers, percentages, counts, and other quantitative statistics.

    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
    আমর
    0.63
     ۲۰
    0.57
     ۴
    0.57
    ♨
    0.57
     Behör
    0.56
     Worte
    0.56
     dispensary
    0.55
     경
    0.55
     часов
    0.55
     ભગવાન
    0.55
    POSITIVE LOGITS
     (.
    1.16
    (.
    1.07
    =.
    0.96
     .
    0.95
     [.
    0.91
     $.
    0.86
     -.
    0.75
    [.
    0.75
     {:.
    0.73
    /.
    0.73
    Activations Density 0.220%

    No Known Activations