© 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. 59159
    Prev
    Next
    INDEX
    Explanations

    sounds of amusement

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

    The neuron strongly responds to onomatopoeic or descriptive words for laughter and amused vocalizations (e.g. chuckle, giggle, cackle).

    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
    ⚋
    -2.44
    </sub>
    -2.28
    氿
    -2.23
     необхідно
    -2.17
    杙
    -2.13
    啭
    -2.11
    歘
    -2.09
    ména
    -2.08
     entspre
    -2.03
     acclaimed
    -2.00
    POSITIVE LOGITS
    $
    2.61
     
    2.38
    ");
    2.36
    .
    2.22
     weiße
    2.16
    ",
    2.03
    ’
    2.00
    ");
    1.98
     grüne
    1.98
    ',
    1.95
    Activations Density 0.001%

    No Known Activations