© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    days and dates

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

    The neuron is selectively activating on numeric tokens formatted as floating‐point decimals.

    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
     авиа
    0.88
     разру
    0.77
    H
    0.75
     офи
    0.71
    ни
    0.69
    V
    0.68
    egrave
    0.68
     обучение
    0.68
     обору
    0.67
     проведен
    0.67
    POSITIVE LOGITS
     paradoxical
    0.80
     whak
    0.79
     publicity
    0.77
     thatch
    0.77
     treści
    0.75
     ratchet
    0.73
    বার্তা
    0.73
     gjør
    0.71
    ؍
    0.71
     micelles
    0.70
    Activations Density 0.001%

    No Known Activations