© 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. 9086
    Prev
    Next
    INDEX
    Explanations

    inflation and historical data

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

    This neuron detects numeric tokens representing real-valued quantities (decimal numbers) such as currency amounts or exchange‐rate 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
     ट
    0.70
     capace
    0.67
     Prüfung
    0.66
     kurzen
    0.65
     스프
    0.63
     SUSY
    0.61
     П
    0.61
    ^+,
    0.61
     प्रकरण
    0.61
     svojoj
    0.61
    POSITIVE LOGITS
    那天
    0.67
     was
    0.66
    ureau
    0.66
    いていた
    0.66
    BarButtonItem
    0.65
    was
    0.64
    当時の
    0.64
    restaurants
    0.63
    Historic
    0.63
    Restaurants
    0.63
    Activations Density 0.007%

    No Known Activations