© 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. 6080
    Prev
    Next
    INDEX
    Explanations

    pygame.display.set_mode

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

    The neuron primarily activates on numeric expressions (numbers and numeric tokens).

    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
    担忧
    0.78
    輸送
    0.76
    嘭
    0.76
    出
    0.74
     erneut
    0.73
    ༘
    0.73
    RetResult
    0.71
    棂
    0.71
    战斗
    0.70
    最も
    0.70
    POSITIVE LOGITS
    al
    1.09
    ol
    1.01
    el
    0.98
    ac
    0.97
    edio
    0.97
    en
    0.93
    ed
    0.89
    is
    0.87
    us
    0.86
    an
    0.86
    Activations Density 0.000%

    No Known Activations