© 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. 13522
    Prev
    Next
    INDEX
    Explanations

    federal legal and governmental terms

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

    federal laws, court, statutes

    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
     in
    0.70
    ని
    0.67
     slopes
    0.62
     argent
    0.62
    在
    0.62
    லய
    0.60
    ين
    0.59
     Fundación
    0.59
    م
    0.59
     yks
    0.57
    POSITIVE LOGITS
    ederal
    0.70
     federally
    0.68
    Federal
    0.66
     federal
    0.64
    federal
    0.63
    FEDERAL
    0.56
     ফেডার
    0.55
    諌
    0.54
    State
    0.53
     федера
    0.51
    Activations Density 0.048%

    No Known Activations