© 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. 34-GEMMASCOPE-RES-131K
    7. 47138
    Prev
    Next
    INDEX
    Explanations

    budget and fiscal matters

    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
    Negative Logits
     בארץ
    -1.09
    ių
    -1.05
    matchCondition
    -1.00
     saisi
    -0.97
     valioso
    -0.97
     Allociné
    -0.96
    offsetHeight
    -0.94
    CodeDom
    -0.94
    merkung
    -0.92
     baffling
    -0.91
    POSITIVE LOGITS
     fiscal
    1.95
     budget
    1.59
     deficit
    1.56
     revenue
    1.48
     balanced
    1.42
     Fiscal
    1.38
    Fiscal
    1.34
    Balancing
    1.34
     balancing
    1.34
    revenue
    1.32
    Activations Density 0.069%

    No Known Activations