© 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. 19393
    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
    镦
    -3.06
     Februari
    -2.34
    たびに
    -2.25
    ㍑
    -2.20
    Ꮌ
    -2.17
     perdana
    -2.16
    ⡦
    -2.14
     Desember
    -2.09
     Jumat
    -2.09
     bianco
    -2.09
    POSITIVE LOGITS
    ↵
    2.77
    ).
    2.22
    ’
    2.19
     “
    2.13
    紧接着
    2.05
    とはいえ
    2.02
     biggest
    2.00
    を設置
    1.99
     jamás
    1.98
     allerdings
    1.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.