© 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. 65689
    Prev
    Next
    INDEX
    Explanations

    executive, chief, director, president, ceo

    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
    科目
    -0.81
    glä
    -0.76
    рк
    -0.75
    уз
    -0.75
    zędu
    -0.73
     Zusammensetzung
    -0.72
    atorul
    -0.72
     refugi
    -0.71
    ırs
    -0.70
     Krankheiten
    -0.70
    POSITIVE LOGITS
     president
    3.66
     President
    3.34
    President
    2.92
    president
    2.78
     PRESIDENT
    2.36
     CEO
    2.31
     owner
    2.14
     президента
    2.02
     presidente
    2.02
     vice
    2.02
    Activations Density 0.060%

    No Known Activations