© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2550
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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_16_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
    2
    1.38
    在
    1.31
    도
    1.22
    1
    1.20
    for
    1.16
     for
    1.09
     in
    1.02
    もら
    1.01
    ও
    0.94
    も
    0.90
    POSITIVE LOGITS
    0.88
     is
    0.76
    )
    0.76
     on
    0.73
     a
    0.73
     to
    0.71
    志森
    0.68
    üyor
    0.68
     มัน
    0.68
    ্পনিক
    0.61
    Activations Density 0.489%

    No Known Activations