© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129909
    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
    較
    -1.01
    𝑙
    -0.88
    已經
    -0.87
    tét
    -0.87
     both
    -0.85
    توان
    -0.84
     парамет
    -0.84
    تع
    -0.82
    verhält
    -0.81
    彼は
    -0.80
    POSITIVE LOGITS
    膈
    1.06
    mpagne
    1.04
     '*'
    0.99
     אביב
    0.97
    פיה
    0.96
    骓
    0.96
    愕
    0.95
     '+'
    0.94
     lastname
    0.92
    caus
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.