© 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. 124628
    Prev
    Next
    INDEX
    Explanations

    international and specific terminology

    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
    Поэтому
    -1.48
    cazione
    -1.46
     після
    -1.43
     With
    -1.38
     to
    -1.34
     дуже
    -1.33
     at
    -1.33
    _()
    -1.31
     because
    -1.30
     питання
    -1.28
    POSITIVE LOGITS
     they
    1.62
     tabac
    1.61
     gâteau
    1.56
    鱚
    1.52
     alho
    1.49
    umentar
    1.48
     rouleau
    1.42
     tuin
    1.39
     takim
    1.38
    읭
    1.38
    Activations Density 0.066%

    No Known Activations