© 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. 6947
    Prev
    Next
    INDEX
    Explanations

    youtube

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    也
    -2.17
    i
    -1.97
    在我
    -1.91
    就
    -1.88
    甚至
    -1.87
     dopo
    -1.81
    
    -1.77
     was
    -1.73
     stata
    -1.70
     Misalnya
    -1.67
    POSITIVE LOGITS
    对方的
    2.28
    紆
    1.66
    nessy
    1.64
    唖
    1.61
     arvo
    1.60
    ients
    1.59
    ynchronously
    1.57
     všem
    1.56
    ACCIÓN
    1.55
    嫉妒
    1.54
    Activations Density 0.013%

    No Known Activations