© 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. 69119
    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
     If
    -2.69
    蕯
    -2.38
     想
    -2.19
    
    -2.16
     可以
    -2.13
    ٣
    -2.08
    😈
    -2.06
     There
    -2.05
    ✌
    -2.05
    💪
    -2.03
    POSITIVE LOGITS
    3
    2.75
    ↵
    2.58
    7
    2.42
    1
    2.41
    8
    2.33
     небольшой
    2.17
     vergleich
    2.03
     некоторых
    2.00
    ஂ
    1.95
     самая
    1.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.