© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27816
    Prev
    Next
    INDEX
    Explanations

    democracy and progressive

    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_40_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
     proto
    0.43
     Technologie
    0.41
    技术的
    0.39
     Alto
    0.39
     nl
    0.38
     Astronaut
    0.38
     STP
    0.38
    畲
    0.38
     Astr
    0.38
     aero
    0.38
    POSITIVE LOGITS
     Democracy
    0.57
     democracy
    0.50
    democracy
    0.47
     progressive
    0.45
     democracies
    0.44
     democracia
    0.43
     Progressive
    0.43
     Progressives
    0.43
    Ꮳ
    0.42
    *********/
    0.42
    Activations Density 0.002%

    No Known Activations