© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4407
    Prev
    Next
    INDEX
    Explanations

    constitutions and charters

    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
    НОВ
    -0.78
     experience
    -0.76
    Looks
    -0.72
    谁
    -0.71
    Wen
    -0.71
    स्
    -0.70
    Logout
    -0.69
    Hear
    -0.69
    Комментарий
    -0.68
    Carthy
    -0.68
    POSITIVE LOGITS
     bylaws
    1.83
     constitution
    1.72
     Articles
    1.63
     charter
    1.56
     articles
    1.34
     Charter
    1.30
     statutes
    1.30
     Constitution
    1.27
    Constitution
    1.25
     constitutions
    1.24
    Activations Density 0.011%

    No Known Activations