© 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. 11966
    Prev
    Next
    INDEX
    Explanations

    select two folders

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

    The neuron strongly activates on floating‐point numeric tokens (numbers containing a decimal point).

    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
    个
    0.74
     aasta
    0.72
    二维
    0.69
    ર
    0.68
     těch
    0.68
     hvad
    0.67
     godine
    0.66
    دأ
    0.66
     maž
    0.66
    อกาส
    0.66
    POSITIVE LOGITS
     amd
    0.72
    し
    0.71
    時に
    0.70
     Pg
    0.69
     entailed
    0.68
     приве
    0.68
    beding
    0.65
     prostit
    0.65
    に使用
    0.65
     
    0.64
    Activations Density 0.000%

    No Known Activations