© 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. 5798
    Prev
    Next
    INDEX
    Explanations

    detecting "For example"

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

    The neuron fires most strongly on words that serve as the head of quantitative descriptions or measurements (e.g. “turn” in “turn on,” “run” in “run a 7-day roster,” “inn” in “5-star inn,” “billion” in “4.5-billion-year,” etc.).

    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
    买了
    0.80
    创建一个
    0.79
    жнарод
    0.75
    สมัคร
    0.74
    Chọn
    0.73
    Falls
    0.72
     chọn
    0.71
     انتخاب
    0.70
    启用
    0.69
    ポリシー
    0.69
    POSITIVE LOGITS
    तया
    0.90
    ാ
    0.85
    ل
    0.78
     beginnen
    0.77
    ки
    0.75
    ो
    0.74
     mols
    0.73
     し
    0.73
    बाड़ी
    0.73
    labyrinth
    0.72
    Activations Density 0.000%

    No Known Activations