© 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. 185247
    Prev
    Next
    INDEX
    Explanations

    being after a or be

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

    language diversity and abstract concepts

    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
    nets
    0.56
    thon
    0.55
    uses
    0.54
    users
    0.54
    utas
    0.54
    -
    0.50
      
    0.50
    means
    0.48
    ships
    0.48
    ök
    0.48
    POSITIVE LOGITS
     Differentiation
    0.51
     પાર્ટી
    0.50
    鈁
    0.50
     வால்பேப்ப
    0.48
     ریکارڈ
    0.46
    кала
    0.46
    ран
    0.45
     واللي
    0.44
    ності
    0.44
     Teilen
    0.44
    Activations Density 0.002%

    No Known Activations