© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84362
    Prev
    Next
    INDEX
    Explanations

    Chinese surnames

    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
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -2.44
     '
    -1.92
     
    -1.88
     seiner
    -1.80
     dalších
    -1.72
    眩
    -1.70
    datable
    -1.70
    寒冷
    -1.70
     Ayrıca
    -1.69
     комната
    -1.63
    POSITIVE LOGITS
    可能会
    2.00
     科技
    1.86
    をします
    1.80
    -
    1.78
    可能會
    1.77
     wyn
    1.76
     """
    1.70
     xvi
    1.70
     zoude
    1.68
     风景
    1.67
    Activations Density 0.007%

    No Known Activations