© 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. 10-GEMMASCOPE-RES-131K
    7. 85107
    Prev
    Next
    INDEX
    Explanations

    exquisite, exceedingly, extraordinary

    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
    熥
    -2.63
    ”;
    -2.61
     wth
    -2.58
     delightfully
    -2.36
    
    -2.34
    actéristi
    -2.33
     deliciously
    -2.31
    扨
    -2.31
    當天
    -2.28
     permett
    -2.22
    POSITIVE LOGITS
     exquisite
    3.06
    vantaged
    3.03
     unrelenting
    2.58
     undeniably
    2.52
     extraordinary
    2.45
    瑧
    2.45
     unparalleled
    2.44
     शुर
    2.42
    ’，
    2.36
     notable
    2.34
    Activations Density 0.003%

    No Known Activations