© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 475
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and scientific examples

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

    LaTeX document preamble

    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_53_width_65k_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
     loài
    0.48
    聸
    0.43
    㜌
    0.43
     Mạnh
    0.42
     marshes
    0.42
    ционными
    0.42
     hydroxyl
    0.42
    ໄຂ
    0.41
    煂
    0.41
    chromiumfx
    0.41
    POSITIVE LOGITS
    usepackage
    1.13
    newcommand
    0.99
    renewcommand
    0.97
    newtheorem
    0.97
    def
    0.86
    Declare
    0.78
    setcounter
    0.74
    title
    0.71
    make
    0.71
    providecommand
    0.71
    Activations Density 0.000%

    No Known Activations