© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3600
    Prev
    Next
    INDEX
    Explanations

    numbers and periods

    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
    Negative Logits
     has
    0.55
     be
    0.52
    M
    0.52
    L
    0.51
    in
    0.50
     ਮ
    0.50
    G
    0.50
    H
    0.49
     ג
    0.49
    i
    0.49
    POSITIVE LOGITS
    数が
    0.41
    ና
    0.38
    из
    0.37
    리학
    0.36
    έν
    0.36
    ジタル
    0.36
    꾼
    0.36
    ーン
    0.36
    ومات
    0.35
     shoved
    0.35
    Activations Density 0.147%

    No Known Activations