© 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. 34-GEMMASCOPE-RES-131K
    7. 77236
    Prev
    Next
    INDEX
    Explanations

    words starting with Sud

    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
     informative
    -0.81
    inference
    -0.79
     twinkle
    -0.79
     Janes
    -0.75
     niewiel
    -0.74
     Alab
    -0.73
    CTE
    -0.72
    ajur
    -0.71
     Neues
    -0.69
     Inquiry
    -0.69
    POSITIVE LOGITS
     Sud
    0.91
    Sud
    0.89
    sud
    0.82
     sud
    0.82
     SUD
    0.81
    デーション
    0.72
     invités
    0.72
    haus
    0.71
    ars
    0.70
     Seating
    0.70
    Activations Density 0.031%

    No Known Activations