© 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. 32076
    Prev
    Next
    INDEX
    Explanations

    sense of humor

    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
    çando
    -0.97
     wunder
    -0.84
     progettazione
    -0.83
    ֶּ
    -0.82
     menatap
    -0.81
    Véxase
    -0.81
    savefig
    -0.79
     esplor
    -0.79
    getInputStream
    -0.78
     omin
    -0.77
    POSITIVE LOGITS
     humor
    4.41
     humour
    4.19
     laugh
    3.88
     laughter
    3.83
     humorous
    3.81
     comedy
    3.73
     joke
    3.67
     jokes
    3.66
     laughing
    3.56
     laughed
    3.45
    Activations Density 0.290%

    No Known Activations