© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24564
    Prev
    Next
    INDEX
    Explanations

    population percentages and majorities

    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_all/layer_41_width_262k_l0_big
    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
    routeName
    0.45
    ocaine
    0.43
    苍
    0.41
    Dif
    0.40
     диф
    0.39
    သား
    0.38
    陌生
    0.38
    最优
    0.38
    蔑
    0.38
     tribes
    0.38
    POSITIVE LOGITS
     majority
    0.66
    majority
    0.63
     percentages
    0.57
     percentage
    0.54
     Majority
    0.53
     mayoría
    0.50
     (%)
    0.50
     Percentage
    0.49
    percentage
    0.48
     majorité
    0.48
    Activations Density 0.003%

    No Known Activations