© 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. 34-GEMMASCOPE-RES-131K
    7. 49078
    Prev
    Next
    INDEX
    Explanations

    dialog boxes, menus, and tabs

    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
    うまい
    -0.91
     gegründet
    -0.88
    我跟
    -0.87
     promover
    -0.85
     leggera
    -0.85
    枡
    -0.84
    Noi
    -0.84
     frequenza
    -0.81
     tenemos
    -0.80
     comunità
    -0.80
    POSITIVE LOGITS
     dialog
    0.97
     pane
    0.94
     pels
    0.87
    CXX
    0.84
    commands
    0.84
    兴奋
    0.83
    ₿
    0.82
    LastName
    0.80
    ₱
    0.80
     Bike
    0.80
    Activations Density 0.038%

    No Known Activations