© 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. 14135
    Prev
    Next
    INDEX
    Explanations

    Tucson, Tusculum, Tuscarora, Tuskegee, Harlem

    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
    
    -3.16
    
    -3.14
    ୌ
    -2.75
    
    -2.59
     sizable
    -2.59
     multitude
    -2.59
    
    -2.56
    钲
    -2.55
    ꔛ
    -2.45
    汭
    -2.41
    POSITIVE LOGITS
     あります
    2.44
    ’
    2.33
    
    2.23
    aaaaaa
    2.22
    ۣ
    2.19
    yea
    2.17
     ,‬
    2.16
    庒
    2.14
    屁股
    2.11
    aaaaaaaa
    2.08
    Activations Density 0.014%

    No Known Activations