© 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. 10184
    Prev
    Next
    INDEX
    Explanations

    currency and financial terms

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

    The neuron fires on mentions of currency and exchange‐rate contexts—i.e. words and phrases around monetary values, devaluations, and financial rates.

    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
     epigenetic
    0.64
     mitotic
    0.61
     線
    0.60
     transpos
    0.59
     chromatin
    0.57
    电机
    0.56
     शहद
    0.56
    厸
    0.56
    葶
    0.56
     epithelial
    0.55
    POSITIVE LOGITS
     currency
    2.48
    currency
    2.36
     currencies
    2.34
     Currency
    2.30
    Currency
    2.28
     валю
    2.23
    currencies
    2.14
     dollar
    1.87
     moneda
    1.84
     Dollar
    1.80
    Activations Density 0.221%

    No Known Activations