© 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. 659
    Prev
    Next
    INDEX
    Explanations

    ASP.NET ID attributes

    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
     to
    -0.83
     get
    -0.82
    niska
    -0.82
    rüstung
    -0.82
     Navbar
    -0.81
    GING
    -0.81
    لفة
    -0.80
    マンション
    -0.80
     achieve
    -0.79
     NavBar
    -0.79
    POSITIVE LOGITS
     delegate
    1.08
     delegates
    0.94
    ệu
    0.87
     IDEAS
    0.85
    Interact
    0.85
     plait
    0.84
     Removes
    0.84
     CHART
    0.83
     calms
    0.81
     VENT
    0.80
    Activations Density 0.003%

    No Known Activations