© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47238
    Prev
    Next
    INDEX
    Explanations

    public entities and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     beret
    -0.82
     varandra
    -0.69
    源码
    -0.69
    越來
    -0.68
    kok
    -0.67
     Kedua
    -0.66
     sebagaimana
    -0.65
     تؤ
    -0.65
     permeable
    -0.65
     巧克力
    -0.63
    POSITIVE LOGITS
     public
    2.50
     обще
    1.96
    public
    1.84
    Public
    1.81
     Public
    1.69
    公共
    1.62
     PUBLIC
    1.59
     общественного
    1.52
     gesellschaft
    1.37
     NGO
    1.36
    Activations Density 0.034%

    No Known Activations