© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102223
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions

    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
     by
    -2.03
    1
    -1.94
     for
    -1.81
     through
    -1.72
     two
    -1.59
     during
    -1.58
     three
    -1.57
    ياب
    -1.52
    Not
    -1.51
     shows
    -1.51
    POSITIVE LOGITS
    蛲
    1.76
    嫑
    1.74
     !!!!
    1.71
    
    1.70
    튿
    1.68
     unbelievably
    1.66
    ཌ
    1.64
    autorelease
    1.63
     AMAZING
    1.63
    vensko
    1.60
    Activations Density 0.012%

    No Known Activations