© 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. 34-GEMMASCOPE-RES-131K
    7. 117513
    Prev
    Next
    INDEX
    Explanations

    dependencies and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     nationalists
    -0.79
     tapas
    -0.78
     CRUD
    -0.75
    ěry
    -0.73
    geren
    -0.73
    ʖ
    -0.72
     かけ
    -0.71
    面に
    -0.71
    ϐ
    -0.71
    REVISTA
    -0.70
    POSITIVE LOGITS
     dependencies
    3.69
     libraries
    3.27
     dependency
    3.17
    dependencies
    2.95
    Dependencies
    2.67
     Dependencies
    2.63
    依赖
    2.52
     dependence
    2.50
    dependency
    2.50
     library
    2.48
    Activations Density 0.282%

    No Known Activations