© 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. 8940
    Prev
    Next
    INDEX
    Explanations

    units and imperial conversions

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

    converting measurement units

    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
    员工
    0.57
     сотрудников
    0.56
     şirk
    0.55
     विचारधारा
    0.52
    党委
    0.52
     pernikahan
    0.52
     সাম্প্রদায়িক
    0.51
    <unused11>
    0.51
    私募基金
    0.51
    党员
    0.51
    POSITIVE LOGITS
     conversions
    0.90
     units
    0.88
     centimeters
    0.88
     conversion
    0.87
     centimeter
    0.82
     metric
    0.81
     millimeters
    0.81
    単位
    0.80
     millimeter
    0.78
     kilogram
    0.76
    Activations Density 0.023%

    No Known Activations