© 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. 34-GEMMASCOPE-RES-131K
    7. 108136
    Prev
    Next
    INDEX
    Explanations

    mogul, magnate, tycoon, Mughal

    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_34/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
     shows
    -0.73
     antworten
    -0.67
     Reinigung
    -0.67
     cherry
    -0.63
     Enable
    -0.63
    webp
    -0.62
     Wartung
    -0.62
     coin
    -0.62
    演员
    -0.61
     род
    -0.60
    POSITIVE LOGITS
     mog
    2.59
     Mog
    1.98
    Mog
    1.91
     magn
    1.54
     tycoon
    1.45
    mog
    1.38
     маг
    1.26
     Mughal
    1.21
     mo
    1.13
     Tycoon
    1.13
    Activations Density 0.038%

    No Known Activations