© 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. 42146
    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
    .
    -1.45
    你的
    -1.34
    时间
    -1.30
    9
    -1.24
    本当に
    -1.22
    开始
    -1.18
    
    -1.17
     эпизо
    -1.14
    ౭
    -1.13
    …」
    -1.11
    POSITIVE LOGITS
     everyone
    1.14
     it
    1.13
     belong
    1.11
    ناق
    1.09
    just
    1.09
     That
    1.08
    خرى
    1.07
     because
    1.05
    vrigt
    1.05
    there
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.