© 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. 204572
    Prev
    Next
    INDEX
    Explanations

    . followed by James

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

    conversations about reasons and fading

    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
     municipal
    0.51
     l
    0.51
     la
    0.50
     voter
    0.49
     watering
    0.49
    ‌
    0.49
     administration
    0.48
     piu
    0.48
     more
    0.47
     criminal
    0.47
    POSITIVE LOGITS
    不利
    0.55
     чемпионате
    0.54
     箱
    0.52
     duckys
    0.52
     технологии
    0.50
    奘
    0.49
    有利
    0.48
    '।
    0.48
    乏
    0.48
    有多少
    0.48
    Activations Density 0.001%

    No Known Activations