© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1706
    Prev
    Next
    INDEX
    Explanations

    year numbers

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

    This neuron fires on numeric tokens (digits and numbers), especially years, dates, and other numbers.

    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
    いた
    0.71
    ки
    0.68
    ای
    0.66
    ación
    0.65
     tvor
    0.63
    śmy
    0.63
    り
    0.63
    ر
    0.62
    ু
    0.61
    து
    0.60
    POSITIVE LOGITS
    thirds
    0.81
    nd
    0.71
    THING
    0.71
    trees
    0.71
    years
    0.70
    ′
    0.70
    time
    0.70
    pm
    0.70
    cos
    0.70
    circa
    0.70
    Activations Density 1.657%

    No Known Activations