© 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. 107377
    Prev
    Next
    INDEX
    Explanations

    the number twenty

    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
     how
    -1.34
     four
    -1.11
     which
    -1.02
     had
    -1.01
     five
    -1.00
     in
    -0.96
    Three
    -0.96
     Làm
    -0.94
     three
    -0.93
    errero
    -0.92
    POSITIVE LOGITS
     twenty
    2.19
     Twenty
    2.03
     TWENTY
    1.70
    Twenty
    1.70
     vinte
    1.59
     vingt
    1.57
    twenty
    1.55
    二十
    1.55
     ২
    1.41
     twenties
    1.33
    Activations Density 0.065%

    No Known Activations