© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69999
    Prev
    Next
    INDEX
    Explanations

    United States Congress

    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
     
    -3.13
    *
    -2.42
    甃
    -2.33
     unſ
    -2.30
    “
    -2.19
    2
    -2.16
    that
    -2.14
     teníamos
    -2.09
     неболь
    -2.06
    ?"
    -2.05
    POSITIVE LOGITS
    ܜ
    3.00
     經典
    2.89
     tbe
    2.58
    鼱
    2.56
     紙
    2.56
     tlie
    2.55
    ↵
    2.52
    
    2.50
    镚
    2.44
     階段
    2.38
    Activations Density 0.007%

    No Known Activations