© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11622
    Prev
    Next
    INDEX
    Explanations

    multinational financial

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

    The neuron activates on numeric tokens containing decimal points (floating-point 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_31_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
    ب
    0.74
    高质量
    0.67
     lined
    0.64
     remedied
    0.63
     sized
    0.62
    当年
    0.61
    ມ
    0.60
    да
    0.60
     entreprene
    0.60
    <0x80>
    0.59
    POSITIVE LOGITS
     Firefox
    0.96
     Fokker
    0.92
     Соответ
    0.91
     Эти
    0.90
     ошибки
    0.88
     problemen
    0.87
    чный
    0.87
     Mozilla
    0.86
     Тран
    0.86
     المنت
    0.86
    Activations Density 0.000%

    No Known Activations