© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numerical tokens containing decimal points (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
    νο
    0.84
    လျ
    0.84
    Е
    0.78
    OUS
    0.70
     znacznie
    0.70
    𝘖
    0.70
    ண
    0.70
    ተ
    0.69
    widetilde
    0.68
     учиты
    0.68
    POSITIVE LOGITS
     simples
    0.97
     unassuming
    0.88
    简单
    0.87
     semplice
    0.85
    簡單
    0.84
     Simple
    0.81
    普通的
    0.81
     معمولی
    0.80
    ทั่วไป
    0.79
     simple
    0.78
    Activations Density 1.002%

    No Known Activations