© 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. 105976
    Prev
    Next
    INDEX
    Explanations

    German place names and suffixes

    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
    </b>
    -2.09
    wasn
    -1.87
    .
    -1.66
     It
    -1.63
     The
    -1.56
    ↵↵↵
    -1.52
    vonne
    -1.48
     жк
    -1.48
     tuss
    -1.46
     SOMETHING
    -1.46
    POSITIVE LOGITS
    　　「
    1.87
     with
    1.73
     boasts
    1.64
     that
    1.59
    erano
    1.57
     and
    1.56
    　　[
    1.55
     each
    1.55
    inverno
    1.54
    鬭
    1.54
    Activations Density 0.028%

    No Known Activations