© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    class names and phrases

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

    The neuron strongly activates on numeric tokens (especially multi‐digit or decimal 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
    년간
    0.85
     години
    0.78
    甶
    0.73
    하시는
    0.73
     discussing
    0.72
     година
    0.70
     উদ্দেশ্যে
    0.70
    ت
    0.70
    لی
    0.69
     tahun
    0.69
    POSITIVE LOGITS
     Nils
    1.01
    柟
    1.01
     Gerry
    0.92
     cloves
    0.91
     Lars
    0.89
     Filippo
    0.86
     Ferd
    0.86
     Floral
    0.86
     Hua
    0.85
     Franti
    0.85
    Activations Density 0.000%

    No Known Activations