© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
     to
    -2.23
    になった
    -1.84
     That
    -1.82
     кух
    -1.80
     ด้วย
    -1.73
     aufgrund
    -1.70
    してくれた
    -1.70
     нержа
    -1.70
     Veränder
    -1.70
     tienen
    -1.70
    POSITIVE LOGITS
    '
    2.56
     rosario
    2.02
    you
    1.99
     пребы
    1.97
    You
    1.97
     هایی
    1.95
     the
    1.93
     العالمي
    1.91
    䛗
    1.77
     کردن
    1.77
    Activations Density 0.005%

    No Known Activations