© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2910
    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
     ۹
    -0.89
    wanza
    -0.83
    úb
    -0.80
    kanak
    -0.78
     ۲
    -0.76
    lipo
    -0.75
     Wissenschaft
    -0.75
    ̉
    -0.74
     triển
    -0.73
    adesivo
    -0.73
    POSITIVE LOGITS
     sixteen
    2.06
     XVI
    2.02
     Sixteen
    1.98
     sixteenth
    1.90
    十六
    1.67
     Seventeen
    1.67
     seventeen
    1.64
     XVII
    1.62
     Sixteenth
    1.61
     seventeenth
    1.59
    Activations Density 0.082%

    No Known Activations