© 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-262K
    7. 80895
    Prev
    Next
    INDEX
    Explanations

    four different images, opera, different subsets, SIE file

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zählt
    0.44
    న్‌
    0.44
     Başkanı
    0.43
     eine
    0.43
    生
    0.42
    న్
    0.42
     zentral
    0.42
    льный
    0.42
    kehr
    0.41
    бут
    0.41
    POSITIVE LOGITS
     със
    0.56
     עם
    0.55
     rinsing
    0.54
    ት
    0.53
    umy
    0.51
     имају
    0.50
    workouts
    0.49
     மாசு
    0.49
     प्राय
    0.48
     wineries
    0.47
    Activations Density 0.007%

    No Known Activations