© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123767
    Prev
    Next
    INDEX
    Explanations

    proper names after periods

    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
    。
    -1.52
    ,\\
    -1.48
     ise
    -1.47
     deles
    -1.45
    arkar
    -1.42
     We
    -1.41
    翾
    -1.41
     jūsų
    -1.38
    ](#
    -1.36
          
    -1.36
    POSITIVE LOGITS
     who
    1.48
     vestiges
    1.44
     unless
    1.39
    纔
    1.38
     nikdy
    1.37
     jaké
    1.34
     where
    1.34
     not
    1.34
     还
    1.32
     whom
    1.28
    Activations Density 0.016%

    No Known Activations