© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15207
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially floating-point numbers with decimal points.

    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
     Qualquer
    0.78
    字符串
    0.77
     Depois
    0.74
     Некоторые
    0.72
     ਹ
    0.71
     Mereka
    0.71
     Пор
    0.71
     Су
    0.71
     Corruption
    0.70
     Çocuk
    0.70
    POSITIVE LOGITS
    เดียว
    0.71
    년대
    0.64
    creatic
    0.64
     отвер
    0.63
    лік
    0.62
     ngưỡng
    0.62
    чность
    0.62
    ↓↓
    0.61
    ALITY
    0.60
     predic
    0.60
    Activations Density 0.123%

    No Known Activations