© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    auxiliary operations

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

    The neuron fires strongly on longer, low‐frequency multisyllabic verbs (especially ones formed with common Latin/Greek prefixes and suffixes).

    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
     воздействия
    0.82
     соль
    0.79
    :";
    0.77
     Fuß
    0.77
    ")]
    0.75
     ונ
    0.75
    ாடு
    0.74
    틋
    0.74
     próxima
    0.73
     cuál
    0.73
    POSITIVE LOGITS
    kent
    0.82
    mainframe
    0.77
    ાઇન
    0.77
     psalm
    0.75
     partic
    0.75
    bog
    0.74
     piston
    0.73
    pct
    0.73
    skeleton
    0.73
    Tem
    0.72
    Activations Density 0.002%

    No Known Activations