© 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. 82801
    Prev
    Next
    INDEX
    Explanations

    unicode categorization

    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
    éraires
    -0.89
    níky
    -0.76
    รอง
    -0.74
    iph
    -0.72
    férences
    -0.72
    pen
    -0.71
     untold
    -0.71
     Receiving
    -0.71
    слей
    -0.69
    inhos
    -0.69
    POSITIVE LOGITS
     category
    1.03
     categories
    0.84
    ließ
    0.84
    Kategori
    0.83
    category
    0.83
    digit
    0.83
     kategori
    0.79
     getCategory
    0.79
     категории
    0.78
     classification
    0.77
    Activations Density 0.042%

    No Known Activations