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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7941
    Prev
    Next
    INDEX
    Explanations

    experimental design and statistical analysis

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

    statistical analysis methods and experimental designs in research papers.

    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_10/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
     lópez
    -1.57
     bagay
    -1.50
     rodríguez
    -1.45
    
    -1.44
     vetores
    -1.42
    </th>
    -1.41
     oliveira
    -1.41
     garcía
    -1.40
    < 
    -1.39
     sapat
    -1.38
    POSITIVE LOGITS
     all
    1.65
     by
    1.53
     for
    1.44
     the
    1.33
     ellas
    1.28
    phim
    1.26
     ръ
    1.25
     leider
    1.23
     lieu
    1.20
    camiseta
    1.19
    Activations Density 0.047%

    No Known Activations