© 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. 3765
    Prev
    Next
    INDEX
    Explanations

    Netflix

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

    The neuron activates on numerical tokens—digits, decimals, and punctuation that form number expressions (e.g. measurements, quantities, or ranges).

    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
     or
    1.06
     in
    0.93
     In
    0.88
    In
    0.84
     (
    0.83
    TM
    0.82
    ,
    0.80
     As
    0.79
     ataupun
    0.79
     at
    0.78
    POSITIVE LOGITS
     χρήση
    1.13
     використання
    1.05
     получение
    1.05
     получает
    1.04
     kullanımı
    1.04
     tehdä
    1.00
     chiede
    1.00
     nincs
    0.99
     различни
    0.99
     получить
    0.98
    Activations Density 0.498%

    No Known Activations