© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13421
    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
    ㅂ
    -1.01
     folosi
    -0.98
     사용
    -0.97
     plă
    -0.96
    auw
    -0.96
    ījum
    -0.94
     început
    -0.94
     scris
    -0.94
     participer
    -0.92
     contacting
    -0.91
    POSITIVE LOGITS
     /
    0.92
     Ajoutez
    0.91
    возмо
    0.90
    男人的
    0.90
    悖
    0.90
    jącego
    0.87
    ](
    0.87
     +
    0.85
     Ausdrücke
    0.84
    ulates
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.