© 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. 8597
    Prev
    Next
    INDEX
    Explanations

    scientific, potential, Fourier, feeling

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

    The neuron flags unusually rare or out‐of‐distribution words—that is, tokens that are comparatively uncommon or “surprising” in the text.

    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
    简称
    0.76
    تها
    0.75
     enveloped
    0.75
    卿
    0.75
    ꯠ
    0.75
     AM
    0.73
     Clar
    0.73
     CMT
    0.71
     AT
    0.70
     kendisine
    0.70
    POSITIVE LOGITS
    ic
    0.91
    scissors
    0.77
    нага
    0.74
    Є
    0.74
    يك
    0.73
    arine
    0.73
    Leggi
    0.73
    루
    0.73
    interrupt
    0.72
    ice
    0.71
    Activations Density 0.000%

    No Known Activations