© 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. 10-GEMMASCOPE-RES-131K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

    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
     untuk
    -2.42
     of
    -2.41
    fillment
    -2.09
    偁
    -2.00
    strator
    -1.99
    ocity
    -1.95
    osity
    -1.94
     pentru
    -1.94
     για
    -1.92
    thodoxy
    -1.91
    POSITIVE LOGITS
     emphas
    1.76
     Permits
    1.59
     Kleidung
    1.48
    <bos>
    1.47
     Früchte
    1.45
     napisał
    1.45
     لوازم
    1.43
     Demands
    1.40
     Theft
    1.40
     Wastes
    1.39
    Activations Density 0.013%

    No Known Activations