© 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. 34655
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    3
    -1.01
     trickle
    -0.87
    θη
    -0.81
    まれる
    -0.77
     repeatable
    -0.77
     blade
    -0.77
     teenagers
    -0.75
    ardino
    -0.75
     thirties
    -0.75
     beep
    -0.72
    POSITIVE LOGITS
     ۲۵
    1.54
     twenty
    1.36
     ২
    1.29
    二十四
    1.21
     Twenty
    1.16
    Twenty
    1.15
    twenty
    1.13
     XXV
    1.05
     TWENTY
    1.03
     २
    1.02
    Activations Density 0.091%

    No Known Activations