© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8257
    Prev
    Next
    INDEX
    Explanations

    humorous jokes

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

    humor and jokes

    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_53_width_65k_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
    -(\
    0.40
     निर्दिष्ट
    0.37
    ulières
    0.37
    ㄷ
    0.37
    aminar
    0.36
    Beautiful
    0.36
    =(\
    0.36
    धात
    0.35
    踟
    0.35
     দূ
    0.35
    POSITIVE LOGITS
     humorous
    3.66
     humor
    3.64
     humour
    3.38
     Humor
    3.20
     comedic
    3.13
     comical
    3.02
     comedy
    3.00
     jokes
    2.91
    搞笑
    2.81
     funny
    2.78
    Activations Density 0.288%

    No Known Activations