© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33786
    Prev
    Next
    INDEX
    Explanations

    wordplay and figurative language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    Simply
    0.45
     தீர்
    0.43
     purely
    0.43
    directly
    0.43
    terminal
    0.42
    ⒉
    0.42
    必ず
    0.42
    漃
    0.42
    ジュール
    0.40
     frankly
    0.40
    POSITIVE LOGITS
     metaphorical
    0.67
     figuratively
    0.66
     slang
    0.65
     metaphor
    0.64
     puns
    0.63
     jokingly
    0.61
     allegedly
    0.57
     resembles
    0.57
     gangsters
    0.57
     stereotypical
    0.57
    Activations Density 0.004%

    No Known Activations