© 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. 80784
    Prev
    Next
    INDEX
    Explanations

    code constructs and keywords

    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
    д
    0.49
     живот
    0.42
    XD
    0.41
    δά
    0.41
    ﺗ
    0.40
    наче
    0.39
    ECUT
    0.39
    irlos
    0.39
    目光
    0.39
     ז
    0.39
    POSITIVE LOGITS
     optimised
    0.49
     adiab
    0.47
     modernity
    0.45
     optimizations
    0.45
     rapidez
    0.45
     aperiam
    0.44
     merid
    0.42
     및
    0.42
     beeinfl
    0.42
    および
    0.41
    Activations Density 0.000%

    No Known Activations