© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1531
    Prev
    Next
    INDEX
    Explanations

    yawn, yaw, sleep

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

    The neuron fires on expressive, non-lexical interjections or sound-effect tokens—e.g. elongated vocalizations like “yawn,” “ho-hum,” “yaaaay,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whitman
    -0.79
     Indus
    -0.79
    étais
    -0.75
    udio
    -0.72
    spół
    -0.71
     obses
    -0.69
     veloci
    -0.69
    Deux
    -0.68
    lup
    -0.68
    enderita
    -0.68
    POSITIVE LOGITS
     yawn
    4.38
     yaw
    4.03
     yawning
    3.91
    yaw
    3.16
    Yaw
    3.03
     Yaw
    2.89
    🥱
    1.46
     Y
    1.43
     boste
    1.42
     sleepy
    1.41
    Activations Density 0.009%

    No Known Activations