© 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. 48168
    Prev
    Next
    INDEX
    Explanations

    abstract nouns followed by of

    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
     acoged
    -2.16
     каком
    -2.00
    ありますか
    -1.87
     cómoda
    -1.85
     maravillosa
    -1.84
     durfte
    -1.75
     merkwür
    -1.75
    しましたが
    -1.75
     inolvid
    -1.74
     unglaub
    -1.74
    POSITIVE LOGITS
     of
    11.50
    ของ
    2.20
     折り
    1.76
     jūs
    1.76
     этих
    1.74
    cheiden
    1.69
    这就是
    1.69
     perumahan
    1.66
    通过
    1.66
     ulteriori
    1.66
    Activations Density 4.477%

    No Known Activations