© 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. 105767
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with division

    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
     και
    -1.79
    司马
    -1.66
    そして
    -1.63
    Ɑ
    -1.57
    こんばん
    -1.52
    ᛬
    -1.48
     considerar
    -1.48
    ئية
    -1.47
    ♡♡
    -1.47
    ebab
    -1.45
    POSITIVE LOGITS
    4
    2.33
    3
    2.27
    ↵
    2.14
    5
    2.06
    2
    2.05
    0
    1.98
     is
    1.93
    6
    1.88
    1
    1.78
     which
    1.77
    Activations Density 0.061%

    No Known Activations