© 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. 91666
    Prev
    Next
    INDEX
    Explanations

    stand-up comedy and comedians

    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
     barbie
    -0.79
     hymn
    -0.76
     symbo
    -0.75
     hymns
    -0.72
    coord
    -0.72
     villains
    -0.71
     الترك
    -0.71
     überweisen
    -0.70
    omis
    -0.70
    (!$
    -0.69
    POSITIVE LOGITS
     comedy
    3.56
     Comedy
    3.11
     comedians
    2.98
    Comedy
    2.89
    comedy
    2.73
     comedian
    2.61
     comedic
    2.36
     jokes
    2.08
     humor
    2.00
     laughter
    1.91
    Activations Density 0.091%

    No Known Activations