© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75809
    Prev
    Next
    INDEX
    Explanations

    java package declarations

    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
    ships
    -0.74
     COAST
    -0.73
    liz
    -0.73
     Silva
    -0.73
    htbp
    -0.71
     startIndex
    -0.70
     Coast
    -0.68
    letcher
    -0.67
     Tuesday
    -0.66
     Khan
    -0.66
    POSITIVE LOGITS
     package
    3.56
     Package
    2.97
     packages
    2.95
    Package
    2.81
    package
    2.69
     PACKAGE
    2.69
    PACKAGE
    2.59
     Packages
    2.55
    packageName
    2.27
     pkg
    2.23
    Activations Density 0.085%

    No Known Activations