© 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. 19190
    Prev
    Next
    INDEX
    Explanations

    judicial circuit rules

    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
     Institutionen
    -2.09
    {
    -1.91
    Different
    -1.86
    龱
    -1.76
     этими
    -1.74
     Organisationen
    -1.71
    Usually
    -1.69
    mainAxisSize
    -1.68
     Kriege
    -1.63
    Have
    -1.62
    POSITIVE LOGITS
    出了一
    1.84
     necesitas
    1.70
    鈰
    1.64
    ਗ਼
    1.63
     zrobić
    1.60
    茈
    1.57
    ции
    1.56
    早期
    1.55
    迄
    1.55
    queryInterface
    1.52
    Activations Density 0.047%

    No Known Activations