© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104330
    Prev
    Next
    INDEX
    Explanations

    odd, strange, or unusual

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

    strange peculiar unusual odd

    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_31_width_262k_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
    0.75
    i
    0.73
    );
    0.67
    u
    0.63
    )),
    0.61
    ");
    0.58
    T
    0.58
    a
    0.57
    il
    0.55
    ";
    0.55
    POSITIVE LOGITS
     oddly
    0.72
    ۲
    0.67
     Лит
    0.63
     strangely
    0.61
     lạ
    0.59
     homogé
    0.58
    ೨
    0.57
     estran
    0.57
     آخرین
    0.56
    奇怪
    0.56
    Activations Density 0.066%

    No Known Activations