© 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. 103831
    Prev
    Next
    INDEX
    Explanations

    naming, renaming, called

    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
    τικές
    -0.95
    adering
    -0.87
    ommt
    -0.85
    Приготовление
    -0.80
    Дорогие
    -0.79
    Текст
    -0.79
    yentes
    -0.78
     vklju
    -0.78
    مقدمه
    -0.78
     exponents
    -0.78
    POSITIVE LOGITS
     naming
    5.50
     named
    5.34
     name
    4.47
    naming
    4.16
    命名
    4.16
     Naming
    4.06
    Naming
    4.03
    named
    3.89
     names
    3.80
     Named
    3.72
    Activations Density 0.202%

    No Known Activations