© 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. 31-GEMMASCOPE-2-RES-262K
    7. 201136
    Prev
    Next
    INDEX
    Explanations

    recursive understanding

    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_31_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
    ობს
    0.54
    ických
    0.44
    瑞
    0.44
    ్రె
    0.44
    ਾਬ
    0.43
    ಿಸಿದ
    0.43
     lockdowns
    0.42
     entrances
    0.42
    ຕິດຕ
    0.42
    ز
    0.42
    POSITIVE LOGITS
    String
    0.49
    Book
    0.46
    Kara
    0.44
    +.
    0.43
     मरम्मत
    0.43
     الكتب
    0.43
    Fruit
    0.42
    +",
    0.42
    Casa
    0.42
     Atty
    0.41
    Activations Density 0.000%

    No Known Activations