© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    technical and foreign language phrases

    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
     a
    -1.73
     efforts
    -1.45
     is
    -1.45
     وتح
    -1.41
    端に
    -1.38
     aclarar
    -1.32
     example
    -1.27
    kras
    -1.27
    leine
    -1.26
    อีก
    -1.25
    POSITIVE LOGITS
     what
    1.70
     tuli
    1.48
     kompetisi
    1.30
    ☆☆☆☆
    1.30
     sano
    1.28
     before
    1.27
     tunn
    1.23
    お得
    1.21
    Geograf
    1.21
     puo
    1.20
    Activations Density 0.221%

    No Known Activations