© 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. 74560
    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
    льзя
    -1.08
     should
    -1.04
     if
    -1.00
     when
    -0.96
    sistence
    -0.93
    ingat
    -0.93
    fters
    -0.92
    jured
    -0.91
     寶
    -0.91
     οποία
    -0.91
    POSITIVE LOGITS
     collaborating
    1.02
     diámetro
    0.98
     cordón
    0.96
     Unterschied
    0.95
     montanha
    0.94
     behandelt
    0.93
    İyi
    0.93
    在住
    0.93
     collaboration
    0.92
     aftermath
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.