© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54234
    Prev
    Next
    INDEX
    Explanations

    Greek letters and scientific symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    Greek letters in scientific and mathematical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     have
    -1.98
     efficiently
    -1.77
     Not
    -1.73
     While
    -1.68
     That
    -1.67
     Before
    -1.66
     Often
    -1.64
     brancas
    -1.63
     seeks
    -1.61
    Ꮔ
    -1.59
    POSITIVE LOGITS
    "
    2.27
    亹
    1.78
     \
    1.72
    e
    1.69
    為に
    1.66
     grote
    1.54
    鱨
    1.54
      
    1.54
     betreffende
    1.50
    立马
    1.49
    Activations Density 0.035%

    No Known Activations