© 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. 11655
    Prev
    Next
    INDEX
    Explanations

    IMF and fiscal policy

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

    The neuron strongly activates on numeric tokens—especially years, figures, and other number-related items in financial or economic contexts.

    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
     corporations
    0.67
     customers
    0.63
     salaries
    0.63
     investments
    0.61
    销
    0.59
     Customers
    0.59
     корпора
    0.59
     Gemeinden
    0.58
    銷
    0.56
     substitutional
    0.55
    POSITIVE LOGITS
    IMF
    1.30
     IMF
    1.20
    Fiscal
    0.81
    macro
    0.75
    Macro
    0.73
     Fiscal
    0.73
    fiscal
    0.72
     fiscal
    0.65
    Coffee
    0.64
     Macros
    0.64
    Activations Density 0.145%

    No Known Activations