© 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. 97181
    Prev
    Next
    INDEX
    Explanations

    rules

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

    leading to dinosaurs

    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
     ionized
    0.47
     equator
    0.45
     axit
    0.45
     dedu
    0.44
     रस्सी
    0.42
     ۵
    0.42
     Laurie
    0.41
     کیا
    0.41
    Jon
    0.41
     devotes
    0.41
    POSITIVE LOGITS
    ثناء
    0.54
    нен
    0.46
    َح
    0.46
    तया
    0.43
    美丽的
    0.43
    諾
    0.43
    诺
    0.43
    реа
    0.43
    ну
    0.42
    ᐃ
    0.42
    Activations Density 0.000%

    No Known Activations