© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38407
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical, ink, resin, hair compositions

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

    technical terms and formal language in patents and scientific documents, particularly focusing on chemical compositions and technical specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    白色的
    -1.50
     ฟ
    -1.48
    辂
    -1.48
     нажмите
    -1.46
     klim
    -1.46
     complementos
    -1.45
    création
    -1.45
     ง
    -1.45
     помощью
    -1.44
    黑色的
    -1.43
    POSITIVE LOGITS
    1
    1.73
     these
    1.70
    面對
    1.44
    Regardless
    1.38
    Without
    1.38
     from
    1.37
     that
    1.37
    While
    1.34
     regardless
    1.33
        
    1.32
    Activations Density 0.280%

    No Known Activations