© 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. 119665
    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
     kanan
    -1.16
     tekno
    -1.09
     $#
    -1.09
    issime
    -1.06
    ⌵
    -1.05
     kasih
    -1.04
     monté
    -1.02
     hakk
    -1.01
    product
    -1.01
     jawab
    -1.00
    POSITIVE LOGITS
    tainen
    0.88
    ビュ
    0.88
     บาง
    0.86
     abstrato
    0.85
    ibid
    0.85
    noche
    0.82
    Magnus
    0.81
     encima
    0.81
     Meteorological
    0.81
     Chúa
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.