© 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. 12652
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting decimal‐formatted numbers (floating‐point numerals) in the text.

    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
     njegova
    0.72
    ocard
    0.71
    iert
    0.70
    ű
    0.70
    apanicola
    0.67
     定
    0.66
    auti
    0.66
    hrlich
    0.66
    halb
    0.65
    iatura
    0.65
    POSITIVE LOGITS
    閎
    0.81
     ты
    0.75
    питы
    0.74
    вной
    0.74
     Hok
    0.72
     canadian
    0.72
    คุ
    0.72
    ской
    0.71
    bigsqcup
    0.71
     Text
    0.70
    Activations Density 0.000%

    No Known Activations