© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11942
    Prev
    Next
    INDEX
    Explanations

    Hmong, Opium, Jerusalem, died

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

    vocals and iconic figures

    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
    ')[
    0.44
    ()[
    0.42
     upregulated
    0.41
    num
    0.40
     '${
    0.40
    ].[
    0.40
     HelloWorld
    0.39
    ")[
    0.39
    ]=[
    0.39
     peeled
    0.39
    POSITIVE LOGITS
     meisten
    0.49
     Coolidge
    0.48
     meeste
    0.45
    騫
    0.45
     खूबस
    0.44
    主な
    0.44
     presque
    0.44
    преки
    0.43
    鹫
    0.43
     BOOKS
    0.42
    Activations Density 0.000%

    No Known Activations