© 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. 66515
    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
     get
    -1.11
    しましたが
    -0.96
     zult
    -0.92
     are
    -0.88
     upscale
    -0.88
     connect
    -0.87
    せい
    -0.86
    чила
    -0.86
    じた
    -0.86
     Sky
    -0.85
    POSITIVE LOGITS
     batteri
    1.23
     quarto
    1.05
    olars
    1.05
     varanda
    1.03
     atle
    1.03
     anla
    1.02
     rios
    1.02
    蹓
    1.02
     restaura
    1.02
     blom
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.