© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2820
    Prev
    Next
    INDEX
    Explanations

    /

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

    The neuron selectively activates on numeric tokens—especially decimal‐point numbers as they appear in journal citations.

    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
    鏻
    0.86
     devido
    0.83
     Modules
    0.83
     módulo
    0.81
    IVITY
    0.80
    薁
    0.79
     Debido
    0.79
    你说
    0.79
     материалов
    0.77
     aldosterone
    0.77
    POSITIVE LOGITS
    j
    0.80
    ري
    0.76
    న
    0.75
    ки
    0.73
    佼
    0.73
    на
    0.73
    いた
    0.71
    ко
    0.70
     chees
    0.70
     feste
    0.70
    Activations Density 0.012%

    No Known Activations