© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67526
    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
     your
    -1.91
     this
    -1.91
    蟊
    -1.77
     ponownie
    -1.70
    %
    -1.68
    )」
    -1.67
    orsese
    -1.63
    鼉
    -1.63
     gratuitement
    -1.61
     целью
    -1.60
    POSITIVE LOGITS
     of
    1.86
    期刊论文
    1.64
    ים
    1.59
    mazaki
    1.52
    تمع
    1.47
     jego
    1.45
     يبدو
    1.42
    क़
    1.42
     Tatsache
    1.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.