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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97891
    Prev
    Next
    INDEX
    Explanations

    funny and hilarious

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    getImage
    -0.81
    語り
    -0.77
    र्
    -0.77
    ырг
    -0.73
    normalized
    -0.73
     Yaman
    -0.72
    auro
    -0.70
    spre
    -0.70
    ridescent
    -0.69
     cumple
    -0.68
    POSITIVE LOGITS
     funny
    4.59
    funny
    3.58
     Funny
    3.11
    Funny
    3.05
     funniest
    2.47
     funnier
    2.19
     humorous
    1.97
     amusing
    1.95
     drôle
    1.94
     hilarious
    1.48
    Activations Density 0.022%

    No Known Activations