© 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. 22-GEMMASCOPE-RES-131K
    7. 36380
    Prev
    Next
    INDEX
    Explanations

    .com website addresses

    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_22/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
    ことも
    -1.71
     However
    -1.64
     Thus
    -1.61
     Further
    -1.59
     Therefore
    -1.56
    不仅
    -1.50
     Moreover
    -1.48
     By
    -1.47
     To
    -1.47
     So
    -1.45
    POSITIVE LOGITS
     mye
    1.55
     ajedrez
    1.54
     岁
    1.53
    휀
    1.50
     crédit
    1.49
    婓
    1.49
    妁
    1.47
     icône
    1.47
     produkter
    1.45
     grafik
    1.44
    Activations Density 0.049%

    No Known Activations