© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84709
    Prev
    Next
    INDEX
    Explanations

    mathematical notation in texts

    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_10/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
    砹
    -1.90
     olej
    -1.86
     that
    -1.75
     américains
    -1.70
     動物
    -1.70
    schod
    -1.65
    씀
    -1.63
     estekak
    -1.63
     帆
    -1.62
     intégral
    -1.59
    POSITIVE LOGITS
    ↵↵
    2.13
     muestran
    2.05
    {
    1.98
     tampaknya
    1.89
    CodeDom
    1.82
     derzeit
    1.77
    〼
    1.69
     bukanlah
    1.67
    可以说
    1.65
    alties
    1.62
    Activations Density 0.004%

    No Known Activations