© 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. 2015
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and Roman numerals

    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
     первого
    -1.21
    first
    -1.09
     Erster
    -1.07
     first
    -1.05
     ersten
    -1.01
     eerste
    -0.99
     pierwszym
    -0.98
    梭
    -0.96
     primeros
    -0.96
     primeiros
    -0.96
    POSITIVE LOGITS
     iii
    2.28
     third
    1.99
    iii
    1.96
     secondly
    1.95
     ii
    1.95
     fourth
    1.94
     III
    1.88
    ②
    1.77
     Thirdly
    1.73
     fifth
    1.71
    Activations Density 0.043%

    No Known Activations