© 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. 127359
    Prev
    Next
    INDEX
    Explanations

    Welsh place names

    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
     või
    -1.75
     if
    -1.62
     zamiast
    -1.49
    glück
    -1.38
    StrictEqual
    -1.30
     årene
    -1.29
     vì
    -1.28
    提醒
    -1.27
    hews
    -1.26
    偏偏
    -1.26
    POSITIVE LOGITS
    (!__
    1.60
    ://
    1.52
     bobina
    1.47
    oczes
    1.41
     hastily
    1.38
     censura
    1.37
     ordinario
    1.37
     then
    1.37
     &
    1.36
     literally
    1.36
    Activations Density 0.759%

    No Known Activations