© 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. 21889
    Prev
    Next
    INDEX
    Explanations

    document section headers

    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
     you
    -2.03
    ),
    -1.56
     It
    -1.51
     Again
    -1.49
     می‌توانید
    -1.48
     The
    -1.45
    也不用
    -1.45
    都不能
    -1.45
    MeasureSpec
    -1.41
     \&
    -1.39
    POSITIVE LOGITS
    :
    2.27
    -
    1.50
     tazas
    1.48
     magasiner
    1.48
    ar
    1.45
    IONS
    1.39
     أخرى
    1.37
     priser
    1.34
    是個
    1.32
    狰
    1.32
    Activations Density 0.662%

    No Known Activations