© 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. 14149
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly on numeric tokens containing a decimal point (i.e. 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
    ри
    0.83
    ون
    0.83
    ه‌
    0.82
    นั้น
    0.80
    ونها
    0.79
     imz
    0.77
    ە
    0.76
    ния
    0.75
     worsen
    0.75
    𝙎
    0.75
    POSITIVE LOGITS
    Mutable
    0.81
     привы
    0.76
    お届け
    0.73
     собе
    0.71
     noticia
    0.70
     reje
    0.69
    kamp
    0.68
    拇
    0.68
     estiver
    0.67
     comunicar
    0.67
    Activations Density 0.000%

    No Known Activations