© 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. 15566
    Prev
    Next
    INDEX
    Explanations

    unique, uremia, frequents, Guar Farmers

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

    quotation marks and special symbols in mathematical or scientific notation.

    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
        
    -1.79
     Belakang
    -1.77
     What
    -1.67
     puisque
    -1.63
    已經
    -1.62
     This
    -1.54
     Zustand
    -1.51
     уже
    -1.49
     Gedanke
    -1.48
     営業
    -1.48
    POSITIVE LOGITS
     Révolution
    1.52
    ing
    1.48
    uteurs
    1.46
     広場
    1.46
     viande
    1.45
     geçti
    1.41
    をしていた
    1.41
     flesta
    1.40
    しちゃ
    1.39
    ppings
    1.38
    Activations Density 0.002%

    No Known Activations