© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6247
    Prev
    Next
    INDEX
    Explanations

    Gemma team at Google DeepMind

    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_31_width_16k_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
    2
    0.33
     ομάδα
    0.32
     geodesic
    0.31
    iler
    0.30
     rotated
    0.30
    we
    0.30
    utzer
    0.30
    erv
    0.29
    und
    0.29
    erta
    0.29
    POSITIVE LOGITS
    //*
    0.39
     عندهم
    0.39
    ులు
    0.38
     شما
    0.36
     Jamaica
    0.35
     предлагают
    0.35
     ارائه
    0.34
    dı
    0.34
     فرنسا
    0.34
    gäng
    0.34
    Activations Density 0.068%

    No Known Activations