© 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. 10-GEMMASCOPE-RES-131K
    7. 42717
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

    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_10/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
    produkter
    -0.98
     albedo
    -0.94
    taña
    -0.94
     another
    -0.93
    another
    -0.93
    🧄
    -0.93
     Toutes
    -0.92
     burberry
    -0.92
    🍧
    -0.91
     augusti
    -0.91
    POSITIVE LOGITS
    titis
    1.06
     rebaj
    1.03
     individual
    1.03
    intellij
    1.02
     depuis
    0.96
    }\]
    0.96
     zudem
    0.96
     wood
    0.95
     IConfiguration
    0.93
    rasse
    0.93
    Activations Density 0.075%

    No Known Activations