© 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. 69898
    Prev
    Next
    INDEX
    Explanations

    IDE names

    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
    listdir
    -0.81
     CGI
    -0.78
    ಡಿ
    -0.77
    Biografia
    -0.76
     Saiyan
    -0.76
    ExecuteNonQuery
    -0.75
    Din
    -0.75
     sapp
    -0.74
    QR
    -0.73
    iPhone
    -0.73
    POSITIVE LOGITS
     IDE
    2.81
     Eclipse
    2.16
    IDE
    2.08
    Eclipse
    2.05
     eclipse
    2.03
    eclipse
    1.93
     IntelliJ
    1.73
     ide
    1.52
    vscode
    1.46
     PhpStorm
    1.42
    Activations Density 0.408%

    No Known Activations