© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1133
    Prev
    Next
    INDEX
    Explanations

    want to do

    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
     peinados
    -1.94
     utilizadas
    -1.93
     pintadas
    -1.91
     externas
    -1.88
     descuentos
    -1.85
     impresiones
    -1.85
     seguras
    -1.84
     decorativas
    -1.80
     delgada
    -1.78
     públicas
    -1.77
    POSITIVE LOGITS
     a
    1.93
    -
    1.77
      
    1.68
                
    1.62
     Of
    1.56
    the
    1.48
     They
    1.43
    /
    1.41
     Moreover
    1.40
    .
    1.38
    Activations Density 0.006%

    No Known Activations