© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107956
    Prev
    Next
    INDEX
    Explanations

    jokes and punchlines

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

    The neuron strongly activates on standalone “headline” or “title‐style” phrases and other singled‐out key terms—e.g. show names, punchlines, slogans, list headings—basically any bit of text set off as a title or emphasized label.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Stuhl
    -0.76
     dry
    -0.72
     स्थान
    -0.71
    viendo
    -0.69
     perhaps
    -0.69
     przypad
    -0.68
     золота
    -0.68
    맡
    -0.68
    붙
    -0.68
    DeleteMapping
    -0.67
    POSITIVE LOGITS
     Joke
    1.38
    Joke
    1.19
     punch
    1.15
     joke
    1.14
    joke
    1.05
    weeper
    0.99
    Jokes
    0.98
    punch
    0.96
    SETUP
    0.93
     Joker
    0.92
    Activations Density 0.016%

    No Known Activations