© 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. 10511
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially decimal or 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
    사가
    0.77
    습니다
    0.76
    윰
    0.73
    ковский
    0.73
    的一
    0.72
     ਪ
    0.72
     дзяржа
    0.72
     основным
    0.71
    数量
    0.71
     державного
    0.71
    POSITIVE LOGITS
    nti
    0.86
    اً
    0.84
    du
    0.75
    َن
    0.74
    اش
    0.73
    ras
    0.72
    َا
    0.72
    تا
    0.72
    خستان
    0.72
    لاً
    0.70
    Activations Density 0.000%

    No Known Activations