© 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. 111682
    Prev
    Next
    INDEX
    Explanations

    I know I

    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
    ?’
    -2.02
     When
    -1.72
    ?”
    -1.71
    </h3>
    -1.67
    gucig
    -1.56
    家用
    -1.54
     ebenfalls
    -1.52
    urança
    -1.52
     ”
    -1.46
     نیز
    -1.41
    POSITIVE LOGITS
    Ⴀ
    1.51
    笑容
    1.39
     inclui
    1.28
    ↵
    1.27
     وش
    1.27
     reconoc
    1.26
     мамы
    1.24
    disposing
    1.24
     шесть
    1.23
     oferece
    1.22
    Activations Density 0.023%

    No Known Activations