© 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-65K
    7. 48040
    Prev
    Next
    INDEX
    Explanations

    reports, Highlights, Impurities, sales, X-ray, softer, rendering, dreaming, play, militants

    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_65k_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
    getDay
    0.42
    ROOM
    0.40
    exercise
    0.38
     exercise
    0.37
    ကြောင့်
    0.36
    graduate
    0.36
    卅
    0.35
    ပို
    0.35
     रक्त
    0.35
     çalışt
    0.35
    POSITIVE LOGITS
     Verbindung
    0.44
     Evangelical
    0.43
     professionally
    0.42
     editorials
    0.40
     व्यावसायिक
    0.38
     emails
    0.38
    漏
    0.37
    करे
    0.37
     Ashwin
    0.37
     sermons
    0.37
    Activations Density 0.002%

    No Known Activations