© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68018
    Prev
    Next
    INDEX
    Explanations

    stock, respective, share, languages

    np_acts-logits-general · gemini-2.5-flash-lite

    physical description and gender presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gaskets
    0.53
     a
    0.52
     magnets
    0.50
     wipes
    0.46
     screws
    0.45
     gasket
    0.45
     wheelchairs
    0.45
     diapers
    0.44
     ador
    0.44
    a
    0.44
    POSITIVE LOGITS
    았던
    0.48
    ت
    0.46
     되지
    0.46
    korzyst
    0.46
    ruari
    0.45
    <unused2231>
    0.44
     Hrvats
    0.44
     最後
    0.44
     Geißler
    0.43
     되었다
    0.43
    Activations Density 0.001%

    No Known Activations