© 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. 10605
    Prev
    Next
    INDEX
    Explanations

    relativistic physics concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens—especially monetary amounts, prices, measurements, capacities, dates, times, phone numbers, and other numeric values.

    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
    基础上
    0.51
     generality
    0.49
     shenanigans
    0.47
    运气
    0.47
    typeparam
    0.46
    年份
    0.46
    部分
    0.46
    笏
    0.46
    以来
    0.46
    ดำเนินการ
    0.45
    POSITIVE LOGITS
    ifers
    0.59
    !’
    0.57
    !।
    0.57
    ooli
    0.57
    icas
    0.56
     (.
    0.56
    ‛
    0.55
    ।-
    0.54
     탱크
    0.54
    ‘
    0.54
    Activations Density 0.009%

    No Known Activations