© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58585
    Prev
    Next
    INDEX
    Explanations

    laughter and informal expressions

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

    The neuron fires on expressions of laughter or amusement (e.g. “lol,” “haha,” “hehe,” “ha”).

    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
     dicembre
    -1.77
    %;">
    -1.73
     you
    -1.71
    崑
    -1.62
    when
    -1.55
     glucocortico
    -1.55
     MATHEMATICAL
    -1.54
     була
    -1.52
     with
    -1.50
     by
    -1.48
    POSITIVE LOGITS
    0
    2.13
    ↵
    1.90
    </h2>
    1.81
    がたくさん
    1.74
    k
    1.70
    os
    1.69
     intriguing
    1.62
    秾
    1.60
     cuentan
    1.56
    itrile
    1.55
    Activations Density 0.006%

    No Known Activations