© 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. 83224
    Prev
    Next
    INDEX
    Explanations

    product releases and enhancements

    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
    IFESTYLE
    -1.02
    有一定
    -1.02
    zellan
    -0.98
    有一定的
    -0.96
     senderismo
    -0.95
    Projekt
    -0.95
    gelijk
    -0.93
    Mål
    -0.90
     möglicherweise
    -0.90
    らう
    -0.90
    POSITIVE LOGITS
     customers
    1.48
     enhancements
    1.45
     release
    1.36
     native
    1.31
     capabilities
    1.29
     product
    1.27
     producti
    1.23
    Customers
    1.16
     clientes
    1.16
     releases
    1.16
    Activations Density 0.067%

    No Known Activations