© 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. 83657
    Prev
    Next
    INDEX
    Explanations

    first names and last names

    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
     this
    -2.09
     in
    -1.86
     with
    -1.81
     by
    -1.79
     at
    -1.76
     now
    -1.73
     their
    -1.59
     Perhaps
    -1.55
     any
    -1.52
     both
    -1.45
    POSITIVE LOGITS
    颏
    1.40
     فقط
    1.37
     сайта
    1.37
    ⅘
    1.35
     bandes
    1.33
    ''',
    1.33
    ⅖
    1.31
    
    1.30
     geene
    1.30
    НИЯ
    1.28
    Activations Density 0.073%

    No Known Activations