© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10460
    Prev
    Next
    INDEX
    Explanations

    This neuron selectively activates on numeric tokens (both integers and decimal‐format 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
    ,
    0.62
     ہیں
    0.58
     हैं
    0.56
    、
    0.55
    <strong>
    0.55
     isn
    0.54
    orem
    0.53
     is
    0.52
     gospel
    0.52
    尼
    0.52
    POSITIVE LOGITS
     בשנת
    0.79
    ผู้ชมในสนาม
    0.70
     Cũng
    0.66
     Inglaterra
    0.66
     dilaksanakan
    0.63
     Norwegen
    0.63
     Wikiseite
    0.62
     Yugoslavia
    0.62
     CORPER
    0.61
    ในปี
    0.61
    Activations Density 0.000%

    No Known Activations