© 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. 22-GEMMASCOPE-RES-131K
    7. 71683
    Prev
    Next
    INDEX
    Explanations

    related to buying, customs, or manner

    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
     after
    -2.05
     three
    -1.84
     before
    -1.84
     five
    -1.66
     when
    -1.64
     using
    -1.63
     while
    -1.61
     two
    -1.60
     eight
    -1.58
     four
    -1.57
    POSITIVE LOGITS
     acheter
    1.47
     delightfully
    1.41
     douane
    1.38
     Dinas
    1.37
     maniere
    1.34
     shimmering
    1.34
     .......
    1.32
    栊
    1.30
    
    1.30
     !!!!!
    1.30
    Activations Density 0.030%

    No Known Activations