© 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. 77107
    Prev
    Next
    INDEX
    Explanations

    expressions of amusement

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

    The neuron fires on written expressions of laughter (onomatopoeic laugh words like “cackle,” “chuckle,” “giggles,” “laughing,” 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
     skies
    -0.81
    kapan
    -0.78
     sky
    -0.74
     miền
    -0.73
     wailing
    -0.72
    त्तर
    -0.71
     CMS
    -0.71
    reado
    -0.70
    cader
    -0.70
    rager
    -0.70
    POSITIVE LOGITS
     chuckle
    2.64
     chuckled
    2.53
     giggle
    2.50
     giggles
    2.25
     chuckles
    2.23
     giggled
    2.20
     giggling
    1.84
     laugh
    1.84
    gig
    1.70
     Gig
    1.68
    Activations Density 0.009%

    No Known Activations