© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114187
    Prev
    Next
    INDEX
    Explanations

    money, pay, tickets, or wealth

    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
    Negative Logits
     mesmo
    -1.03
     même
    -1.02
     latter
    -1.02
     doméstico
    -1.00
     swat
    -1.00
     include
    -1.00
     каждой
    -0.97
     каждого
    -0.97
     exists
    -0.95
     لكل
    -0.95
    POSITIVE LOGITS
    ประมาณ
    1.13
    рид
    1.05
     useAppContext
    1.05
     TAMBIÉN
    1.04
    recyclerView
    1.04
    тся
    1.03
    ̍t
    1.02
    ggiato
    1.01
     karet
    1.01
     Selasa
    1.01
    Activations Density 0.086%

    No Known Activations