© 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. 29889
    Prev
    Next
    INDEX
    Explanations

    school class names

    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
    teen
    -0.88
    高校生
    -0.85
     teen
    -0.84
     подрост
    -0.83
     PROGRAM
    -0.82
     teens
    -0.81
    高中
    -0.81
     юно
    -0.81
     freshman
    -0.81
     Ier
    -0.79
    POSITIVE LOGITS
     children
    1.08
     Infant
    0.88
     Mrs
    0.84
     playtime
    0.83
    namon
    0.81
     Medicines
    0.79
     newsletters
    0.79
    Infant
    0.77
    登陆
    0.77
     nitrates
    0.77
    Activations Density 0.017%

    No Known Activations