© 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. 22-GEMMASCOPE-RES-131K
    7. 38239
    Prev
    Next
    INDEX
    Explanations

    laughter and jokes

    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_22/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
     as
    -0.95
     on
    -0.94
     cautious
    -0.87
    AllowUser
    -0.84
     unusually
    -0.83
     There
    -0.80
     vincula
    -0.80
    findOrFail
    -0.80
    案例
    -0.80
     there
    -0.79
    POSITIVE LOGITS
     kidding
    1.88
    Jokes
    1.64
     joking
    1.61
     jokes
    1.50
     Jokes
    1.41
    Jok
    1.40
    jk
    1.39
     jk
    1.38
    joke
    1.37
     sarcas
    1.33
    Activations Density 0.060%

    No Known Activations