© 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. 61272
    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
    ってしまう
    -0.93
    眯
    -0.91
     affirme
    -0.90
     captiv
    -0.88
     recomienda
    -0.86
     ihrem
    -0.84
     melh
    -0.84
     alguns
    -0.84
    🎦
    -0.84
     approximation
    -0.82
    POSITIVE LOGITS
    khó
    1.30
     renewed
    1.20
    א
    1.08
    iramente
    1.05
    ensas
    1.05
    ılar
    1.05
     fisico
    1.05
     पढ़ें
    1.03
    ènes
    1.02
    SAL
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.