© 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. 98781
    Prev
    Next
    INDEX
    Explanations

    metropolitan areas, locations, or organizations

    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
    '
    -2.14
    ！）
    -1.91
     بیش
    -1.79
     martens
    -1.78
    泐
    -1.77
    にゃ
    -1.77
     bestemt
    -1.75
     bygget
    -1.73
    基本上
    -1.71
    豨
    -1.70
    POSITIVE LOGITS
    ↵
    2.22
     sowohl
    2.13
    ’
    2.06
     Our
    2.03
     >
    1.88
     −
    1.87
     Beginn
    1.87
     Then
    1.86
     onze
    1.84
    ’，
    1.83
    Activations Density 0.012%

    No Known Activations