© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    most of

    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
     reinforces
    -1.41
    すること
    -1.40
    ჻
    -1.37
     fateful
    -1.35
     which
    -1.33
     wią
    -1.30
     logra
    -1.30
    petual
    -1.29
     acquires
    -1.27
     sklo
    -1.27
    POSITIVE LOGITS
    ㍑
    1.80
     ว่า
    1.61
     unſ
    1.57
    栳
    1.57
    羮
    1.57
     für
    1.56
    
    1.52
     also
    1.49
     saba
    1.49
     แต่
    1.48
    Activations Density 0.009%

    No Known Activations