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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14890
    Prev
    Next
    INDEX
    Explanations

    sarcasm and irony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     true
    0.57
     confound
    0.56
     conspir
    0.56
    true
    0.55
     امور
    0.53
     uncontroll
    0.53
    犯
    0.53
     unnecessarily
    0.53
     confounded
    0.53
     conclusiones
    0.52
    POSITIVE LOGITS
     conveniently
    0.80
     laughable
    0.78
     irony
    0.75
    呵呵
    0.68
     ironic
    0.68
    Conven
    0.62
     sarcasm
    0.62
    諷
    0.62
     Convenient
    0.61
    🙄
    0.61
    Activations Density 0.157%

    No Known Activations