© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11079
    Prev
    Next
    INDEX
    Explanations

    wedding usage scenarios

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

    The neuron fires on numeric expressions—numbers, dates, durations, measurements, and times.

    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
    縊
    0.83
    景点
    0.82
    습니다
    0.78
    澳洲
    0.78
    igeon
    0.78
    条
    0.77
    構築
    0.76
    вання
    0.75
    隧道
    0.75
     Pursuant
    0.75
    POSITIVE LOGITS
     צו
    0.75
     ต้น
    0.75
     වන
    0.71
     פי
    0.71
    ";}
    0.69
     ล
    0.68
    sons
    0.68
    ه‌ی
    0.68
    Jimmy
    0.68
    Simplify
    0.67
    Activations Density 0.000%

    No Known Activations