© 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. 5001
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to numeric tokens (especially those containing decimal digits).

    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
    ⍵
    0.80
     кош
    0.75
     tertinggi
    0.73
     dati
    0.71
    统一
    0.71
    ваме
    0.71
     ли
    0.71
    व्हाण
    0.71
    ႇ
    0.71
    plik
    0.70
    POSITIVE LOGITS
    [];
    0.75
     contrasts
    0.75
     AppDelegate
    0.72
     rendition
    0.71
     spectators
    0.71
     Cáceres
    0.71
    কী
    0.71
     Spreadsheet
    0.70
     orchestrated
    0.69
    ="'.$
    0.68
    Activations Density 0.001%

    No Known Activations