© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103350
    Prev
    Next
    INDEX
    Explanations

    elected representatives and councils

    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
    Not in Any Lists

    No Comments

    Negative Logits
     مدير
    -0.90
    রে
    -0.80
    onio
    -0.79
     pubblico
    -0.78
    tiba
    -0.77
    toje
    -0.76
    urée
    -0.76
    LINEAR
    -0.76
    ﺣ
    -0.75
    IFICATIONS
    -0.75
    POSITIVE LOGITS
     representative
    2.06
     representatives
    1.93
     representation
    1.78
     councils
    1.68
     council
    1.66
     advisory
    1.63
     elected
    1.62
     Representative
    1.62
    representative
    1.61
     representa
    1.54
    Activations Density 0.028%

    No Known Activations