© 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. 71438
    Prev
    Next
    INDEX
    Explanations

    HTML table and data structures

    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
     of
    -3.33
    n
    -2.20
     or
    -1.89
     We
    -1.87
    ,
    -1.80
    ing
    -1.77
    "
    -1.64
     i
    -1.54
     informée
    -1.52
    諷
    -1.51
    POSITIVE LOGITS
     másik
    1.98
     lade
    1.88
     lille
    1.87
    
    1.84
    archiwizowane
    1.81
     lyd
    1.81
    휀
    1.80
    кроссовки
    1.78
    솝
    1.78
     monter
    1.77
    Activations Density 0.049%

    No Known Activations