© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    The neuron detects floating‐point number 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
    Ş
    0.82
    ті
    0.80
    Č
    0.78
    Ü
    0.75
    Ś
    0.74
    Ça
    0.73
    İ
    0.73
    Bước
    0.72
    จะเป็น
    0.69
    Ć
    0.69
    POSITIVE LOGITS
     muchos
    0.92
     Minkowski
    0.92
     seamen
    0.91
     Djokovic
    0.91
     MRT
    0.91
     অনেকে
    0.89
     Edith
    0.89
     martens
    0.89
     Ignatius
    0.88
     pentes
    0.88
    Activations Density 0.000%

    No Known Activations