© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102922
    Prev
    Next
    INDEX
    Explanations

    division of

    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
     There
    -2.02
     Это
    -1.94
    wiście
    -1.91
     práctica
    -1.83
     That
    -1.81
     in
    -1.80
     numerosas
    -1.79
     принад
    -1.77
     großes
    -1.76
     всі
    -1.75
    POSITIVE LOGITS
    m
    3.48
    o
    2.42
    ⚋
    2.33
    ᚔ
    2.31
     "
    2.28
    h
    2.27
    v
    2.23
    圌
    2.14
    es
    2.05
    ྄
    2.02
    Activations Density 0.019%

    No Known Activations