© 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. 86643
    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
     космети
    -1.05
    дян
    -0.97
     If
    -0.87
    pieler
    -0.84
     Drogen
    -0.84
    selections
    -0.84
    呖
    -0.84
     каталог
    -0.84
    Desc
    -0.81
    ⏲
    -0.81
    POSITIVE LOGITS
     errichtet
    1.05
    珣
    0.98
     poslední
    0.95
    出于
    0.93
    adona
    0.92
    ៗ
    0.91
     Radical
    0.91
     reacciones
    0.91
    ERRA
    0.90
     chronic
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.