© 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. 60368
    Prev
    Next
    INDEX
    Explanations

    academic courses and textbooks

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

    references to books, textbooks, manuals, and academic publications.

    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
    Research
    -0.82
    research
    -0.80
     schwarze
    -0.79
    Kaip
    -0.78
    нрави
    -0.76
     pomys
    -0.75
     research
    -0.75
     RESEARCH
    -0.74
     olej
    -0.74
    énez
    -0.72
    POSITIVE LOGITS
     course
    1.35
     textbook
    1.06
     Course
    1.05
     tutorial
    1.04
    Course
    1.04
     courses
    1.04
     учеб
    1.01
     manual
    0.97
    course
    0.96
    教程
    0.96
    Activations Density 0.005%

    No Known Activations