© 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. 105456
    Prev
    Next
    INDEX
    Explanations

    do something

    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
    蒾
    -2.09
    selbe
    -1.98
     verrou
    -1.95
    퐼
    -1.88
    Kommentare
    -1.88
    峩
    -1.87
    ⚋
    -1.84
    镚
    -1.81
    
    -1.79
     несколь
    -1.78
    POSITIVE LOGITS
     in
    2.72
     from
    2.48
     for
    2.39
     with
    2.38
     he
    1.91
     姫
    1.91
     by
    1.87
    $
    1.76
     about
    1.67
    “
    1.66
    Activations Density 0.009%

    No Known Activations