© 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. 14528
    Prev
    Next
    INDEX
    Explanations

    celestial, water, glyphosate

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

    The neuron is keyed to spotting numeric values (especially floating‐point numbers) in the text.

    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
    ع
    0.80
    ف
    0.80
    の方が
    0.77
    給
    0.75
     give
    0.75
     ON
    0.68
     Anticip
    0.66
     enfim
    0.65
    か
    0.65
     Ultrasound
    0.64
    POSITIVE LOGITS
    Сегодня
    0.79
     Сегодня
    0.76
    reality
    0.68
     modernity
    0.67
    omeness
    0.67
    тинен
    0.66
    𝐼
    0.65
    יום
    0.63
    今日の
    0.63
    isture
    0.63
    Activations Density 0.107%

    No Known Activations