© 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. 103062
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, ordinal numbers

    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
     eight
    -0.83
    8
    -0.82
    八
    -0.77
    bx
    -0.73
     månader
    -0.70
    起こ
    -0.69
     Hell
    -0.69
     Eight
    -0.68
    hető
    -0.67
    lient
    -0.66
    POSITIVE LOGITS
     ten
    1.27
    Ten
    1.24
     tenth
    1.18
     ۱۰
    1.15
     Tenth
    1.12
     Ten
    1.06
    十
    1.02
    ۱۰
    0.94
     TEN
    0.91
    TEN
    0.84
    Activations Density 0.033%

    No Known Activations