© 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. 8914
    Prev
    Next
    INDEX
    Explanations

    currency symbols and names

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

    The neuron activates on numeric tokens and digit sequences (e.g. prices, amounts, dates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numeric digits within large numbers, especially in price or financial contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    numerical figures, especially currency-denominated amounts, prices, dates, percentages, and other large financial statistics.

    oai_token-act-pair · gpt-5Triggered 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
    试图
    0.68
    美国
    0.67
    甜
    0.66
    associated
    0.66
    ESPN
    0.65
    combined
    0.64
    Connecticut
    0.62
    Washington
    0.61
    北美
    0.61
    Associated
    0.60
    POSITIVE LOGITS
     rupees
    0.95
     lira
    0.89
     Rupees
    0.87
     mensual
    0.87
     bulan
    0.82
     ₹
    0.82
     Rs
    0.80
     kada
    0.79
     denars
    0.79
     рублей
    0.79
    Activations Density 0.257%

    No Known Activations