© 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. 75716
    Prev
    Next
    INDEX
    Explanations

    graduate education and medical training

    np_acts-logits-general · gemini-2.5-flash-lite

    contexts related to education, particularly medical, nursing, or graduate education.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    晚了
    -0.81
    商场
    -0.80
    Recept
    -0.78
     übri
    -0.77
    Livro
    -0.74
    ゲ
    -0.73
    ibição
    -0.72
    ními
    -0.72
    arama
    -0.71
     smokes
    -0.70
    POSITIVE LOGITS
     education
    3.11
     educación
    2.27
    education
    2.16
     Education
    2.14
    教育
    2.03
     educação
    2.02
    Education
    1.95
     EDUCATION
    1.91
     pendidikan
    1.69
     educational
    1.64
    Activations Density 0.036%

    No Known Activations