© 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. 14526
    Prev
    Next
    INDEX
    Explanations

    currency symbols

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

    This neuron primarily detects numeric tokens—numbers, dates, statistics, and similar quantitative figures.

    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
    ف
    0.88
    ﺴ
    0.82
    ﺼ
    0.82
    ۹
    0.81
     Бы
    0.77
    س
    0.75
    зы
    0.75
    ﺒ
    0.73
     يحدث
    0.72
     kerusakan
    0.72
    POSITIVE LOGITS
     என
    0.74
    ꯣ
    0.70
    लान
    0.69
    uggling
    0.68
    bate
    0.68
     certes
    0.68
     లేదా
    0.67
    Dart
    0.67
    لام
    0.66
    সাম
    0.66
    Activations Density 0.003%

    No Known Activations