© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34953
    Prev
    Next
    INDEX
    Explanations

    numbers in multiple languages

    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_22/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
     countless
    -0.85
     tons
    -0.79
    乍
    -0.78
    ammer
    -0.77
     many
    -0.77
    ālā
    -0.76
    columnwidth
    -0.75
     dozens
    -0.74
    conci
    -0.74
    ciences
    -0.73
    POSITIVE LOGITS
     तीन
    1.25
     trzech
    1.15
    three
    1.09
     three
    1.07
    三个
    1.05
    三個
    1.01
     ثلاثة
    0.98
     ketiga
    0.96
     pozosta
    0.96
     two
    0.95
    Activations Density 0.116%

    No Known Activations