© 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. 15919
    Prev
    Next
    INDEX
    Explanations

    current president or capital

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

    The neuron fires on descriptions of sports performance and career milestones—especially mentions of scoring plays (like “scoring a try”), season or contract durations, and related player statistics.

    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
    เหล่านี้
    0.64
    ressions
    0.63
     diversa
    0.61
     mags
    0.59
     bureaucr
    0.59
     خوبی
    0.59
     विविध
    0.58
     capaces
    0.58
     ผ้า
    0.58
    οντας
    0.57
    POSITIVE LOGITS
     first
    1.30
     pertama
    1.13
     primeira
    1.12
    第一个
    1.11
     primeiro
    1.10
     первого
    1.10
     প্রথম
    1.09
     첫
    1.08
     पहली
    1.07
     eerste
    1.07
    Activations Density 0.794%

    No Known Activations