© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2464
    Prev
    Next
    INDEX
    Explanations

    weird, odd, strange

    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/layer_40_width_262k_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
    ณฑ์
    0.39
    Ac
    0.37
    に示す
    0.37
    Rav
    0.35
    বাহিত
    0.35
     क्लियर
    0.34
    שׁ
    0.34
    別
    0.34
    ted
    0.33
     दिखाना
    0.33
    POSITIVE LOGITS
     weird
    1.16
     odd
    1.05
     strange
    1.05
    奇怪
    1.00
    weird
    0.98
     Weird
    0.95
     oddly
    0.93
     bizarre
    0.93
     quirks
    0.93
     quirk
    0.90
    Activations Density 0.018%

    No Known Activations