© 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. 9636
    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
     of
    -2.97
    骜
    -2.42
     '
    -2.42
    嶠
    -2.39
     unwavering
    -2.33
     With
    -2.33
     gettin
    -2.33
    僭
    -2.28
    媄
    -2.19
    艫
    -2.14
    POSITIVE LOGITS
    Doesn
    2.70
     DURING
    2.70
    屺
    2.64
    during
    2.55
    籥
    2.50
     какую
    2.41
    が付いて
    2.38
    すれば
    2.34
    すすめ
    2.33
    在他的
    2.33
    Activations Density 0.001%

    No Known Activations