© 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. 9168
    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
     are
    -1.04
     แต่
    -0.98
    ạm
    -0.96
    ਫ਼
    -0.94
    👱
    -0.93
    されない
    -0.90
     zwar
    -0.90
     квіт
    -0.89
     velha
    -0.89
    müş
    -0.89
    POSITIVE LOGITS
    珦
    1.09
     voor
    1.01
     gustado
    1.00
     炎
    1.00
     }}$
    0.98
    LogUtils
    0.95
     crossorigin
    0.94
    rable
    0.94
    Still
    0.93
    isLoading
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.