© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7035
    Prev
    Next
    INDEX
    Explanations

    total, all, including

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

    This neuron activates on mentions of quantified counts or statistics—words that label measured quantities of people, items, or events.

    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
    Zobacz
    0.68
     중요한
    0.67
     కొంత
    0.66
     একাধিক
    0.65
     예
    0.65
    Whenever
    0.64
     Whenever
    0.63
     অনে
    0.63
    ?</
    0.63
    understand
    0.63
    POSITIVE LOGITS
     ukup
    1.09
     insgesamt
    1.01
    合計
    0.98
     каждая
    0.98
     total
    0.95
     включая
    0.94
     மொத்தம்
    0.94
     toplam
    0.93
     કુલ
    0.93
     répart
    0.91
    Activations Density 1.094%

    No Known Activations