© 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. 104066
    Prev
    Next
    INDEX
    Explanations

    occupational therapy and play

    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
     înc
    -1.33
     how
    -1.31
    輒
    -1.28
    how
    -1.22
     bewust
    -1.22
    ']?>
    -1.20
    Lla
    -1.19
     refleja
    -1.16
    utenants
    -1.13
    になるので
    -1.11
    POSITIVE LOGITS
     również
    1.30
     tudi
    1.25
     anche
    1.22
    sä
    1.17
     dipu
    1.13
     autre
    1.10
     Cataluña
    1.10
     japones
    1.09
     ваш
    1.09
     already
    1.09
    Activations Density 0.059%

    No Known Activations