© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44261
    Prev
    Next
    INDEX
    Explanations

    puns and jokes

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

    jokes and puns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vehement
    0.44
     Balashov
    0.41
    Richt
    0.40
     despacho
    0.39
    ≪
    0.38
    ±
    0.38
     Richt
    0.38
    unarod
    0.35
     kHz
    0.35
    ︽
    0.35
    POSITIVE LOGITS
     puns
    0.76
     jokes
    0.71
     joke
    0.66
    joke
    0.64
    jokes
    0.63
     Jokes
    0.57
     Joke
    0.56
    Joke
    0.56
     joked
    0.51
     வாழைப்பழ
    0.51
    Activations Density 0.032%

    No Known Activations