© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    Hugging Face, SageMaker, Robinhood, Bitstamp

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

    The neuron selectively activates on long, multisyllabic terms—especially those built from Latin/Greek roots—that are common in scientific, technical, or biomedical contexts.

    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
     nanti
    0.46
     bernama
    0.46
     aprox
    0.44
    <unused61>
    0.44
     réellement
    0.42
    pictured
    0.42
     Abgerufen
    0.41
     przyst
    0.41
     néanmoins
    0.40
     siitä
    0.40
    POSITIVE LOGITS
    ภัณฑ์
    0.60
    urethane
    0.54
     मिश्रा
    0.49
    ulence
    0.47
    ilization
    0.46
    лення
    0.46
    ulfillment
    0.45
    黄
    0.45
    opathology
    0.45
    妮
    0.45
    Activations Density 0.375%

    No Known Activations