© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71026
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces and German

    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
     it
    -1.73
    while
    -1.72
     in
    -1.67
     while
    -1.61
     to
    -1.48
    sellor
    -1.45
    ↵↵
    -1.43
     terwijl
    -1.38
     since
    -1.34
    k
    -1.34
    POSITIVE LOGITS
    ᕱ
    1.47
     kupa
    1.46
     baumwolle
    1.42
     sors
    1.42
     ruh
    1.39
     mets
    1.35
     ders
    1.35
     sprüche
    1.34
     katt
    1.33
     filles
    1.32
    Activations Density 0.017%

    No Known Activations