© 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. 10-GEMMASCOPE-RES-131K
    7. 13347
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and reaction

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

    This neuron fires on tokens that mark nonverbal or emotive stage directions and reactions—like “(smile)”, “lol”, “laugh”, “grin” and the surrounding parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     a
    -1.70
    er
    -1.70
    H
    -1.70
     F
    -1.61
    E
    -1.58
     you
    -1.56
    with
    -1.48
    Ņ
    -1.46
    ct
    -1.45
    N
    -1.45
    POSITIVE LOGITS
     الأولى
    1.62
     húmedo
    1.60
     rústico
    1.52
    あるので
    1.52
    Введение
    1.50
    年輕
    1.50
     FOURTH
    1.48
    delicious
    1.48
     macetas
    1.46
    ihnachts
    1.44
    Activations Density 0.001%

    No Known Activations