© 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. 22274
    Prev
    Next
    INDEX
    Explanations

    Chinese Guo surnames and Chinese places

    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
    跸
    -2.44
    ᥬ
    -2.39
     Namun
    -2.38
    immen
    -2.36
    罴
    -2.34
    尨
    -2.33
     banter
    -2.28
    wahati
    -2.28
    
    -2.25
    坶
    -2.25
    POSITIVE LOGITS
    {
    3.03
    </em>
    3.00
    er
    2.98
    们的
    2.80
    at
    2.80
    in
    2.78
    </h4>
    2.66
    ’
    2.64
     et
    2.58
    ，《
    2.55
    Activations Density 0.003%

    No Known Activations