© 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. 80677
    Prev
    Next
    INDEX
    Explanations

    words starting with Au or Aug

    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
     vellum
    -0.73
     disintegration
    -0.71
    即便是
    -0.70
    четов
    -0.69
    δες
    -0.69
    Dez
    -0.69
    efec
    -0.69
     debated
    -0.68
     Sheldon
    -0.68
    途中で
    -0.68
    POSITIVE LOGITS
     au
    1.00
     ау
    0.98
     AUG
    0.91
     Au
    0.88
    aug
    0.88
     Aug
    0.88
    thentic
    0.88
     contraire
    0.85
    authentic
    0.82
     audi
    0.82
    Activations Density 0.020%

    No Known Activations