© 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. 128368
    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
    或者
    -2.13
     Nonetheless
    -1.91
    n
    -1.89
     =
    -1.81
    s
    -1.80
     Nevertheless
    -1.71
    特别是
    -1.70
    但这
    -1.70
    ，
    -1.65
    “
    -1.63
    POSITIVE LOGITS
    璈
    1.91
    ⃙
    1.89
    ྜ
    1.76
    iſter
    1.74
    ＞＞
    1.74
     vín
    1.68
    ࿙
    1.64
    嵛
    1.64
    鏷
    1.63
    咳咳
    1.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.