© 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. 47648
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Aufenthalt
    -0.95
     начинают
    -0.93
     comunicação
    -0.89
     Calidad
    -0.88
     керами
    -0.86
    いただきたい
    -0.86
    角落
    -0.86
    殽
    -0.85
    vind
    -0.85
     categor
    -0.85
    POSITIVE LOGITS
     tlie
    1.02
    Sebelum
    0.99
     Agrawal
    0.96
     toneladas
    0.94
    Sekarang
    0.92
    Buat
    0.91
     tbe
    0.91
    pilih
    0.90
    CASA
    0.88
    Banyak
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.