© 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. 2466
    Prev
    Next
    INDEX
    Explanations

    mix of things

    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
    хьтан
    -0.92
     wł
    -0.77
     tener
    -0.75
     busted
    -0.75
    限界
    -0.75
    ございます
    -0.74
     번째
    -0.73
     widget
    -0.73
     dois
    -0.73
     serca
    -0.73
    POSITIVE LOGITS
     mixture
    2.19
     mix
    2.11
     mosaic
    1.88
     medley
    1.87
     kale
    1.82
     patchwork
    1.82
     cocktail
    1.80
     melange
    1.64
     maze
    1.63
     stew
    1.59
    Activations Density 0.094%

    No Known Activations