© 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. 22-GEMMASCOPE-RES-131K
    7. 15919
    Prev
    Next
    INDEX
    Explanations

    SQL statements and XML configurations

    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_22/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
     acrylique
    -0.97
    任何
    -0.97
     dising
    -0.92
     Requires
    -0.91
    MessageTagHelper
    -0.90
    AddTagHelper
    -0.89
    
    -0.89
    nende
    -0.88
     conscientes
    -0.87
    ')));
    -0.85
    POSITIVE LOGITS
     which
    0.96
     our
    0.93
     year
    0.92
     locations
    0.89
     первую
    0.88
     занятия
    0.87
    före
    0.87
     estilos
    0.86
     семь
    0.86
     남자
    0.85
    Activations Density 0.010%

    No Known Activations