© 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. 34-GEMMASCOPE-RES-131K
    4. 118213
    Prev
    Next
    INDEX
    Explanations

    rational numbers and durations

    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
     Thelma
    -0.85
     double
    -0.82
    واء
    -0.73
    double
    -0.72
     està
    -0.71
     آن
    -0.69
    Double
    -0.68
    𝐛
    -0.68
     analyze
    -0.68
    brook
    -0.67
    POSITIVE LOGITS
     Money
    1.43
     Rational
    1.39
     Duration
    1.38
     Quantity
    1.33
    Money
    1.33
    Quantity
    1.27
    Rational
    1.23
    Duration
    1.21
    rational
    1.17
     Ratio
    1.09
    Activations Density 0.138%

    No Known Activations