© 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. 12465
    Prev
    Next
    INDEX
    Explanations

    called + names/descriptions

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

    The neuron strongly activates on numeric tokens with decimal points (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
     gồm
    0.75
     olan
    0.73
     codimension
    0.72
     género
    0.68
    typeof
    0.67
     ünlü
    0.66
    name
    0.66
     (=
    0.66
    typedef
    0.65
     fewer
    0.64
    POSITIVE LOGITS
    𐱃
    0.77
    وس
    0.73
    स
    0.71
     दाब
    0.70
     วัน
    0.70
    inescence
    0.69
     Rumah
    0.69
    OGRAPHIC
    0.69
    वास
    0.69
     Нача
    0.68
    Activations Density 0.020%

    No Known Activations