© 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. 22-GEMMASCOPE-RES-131K
    7. 127771
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of economic sectors or policy shifts—terms around diversifying, shifting, or growing parts of the economy.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    economic growth and productivity

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     paznok
    -1.85
    zaamheid
    -1.55
    Bisous
    -1.52
     hábit
    -1.49
     esquecer
    -1.43
    Their
    -1.37
    Each
    -1.36
     आपके
    -1.34
    Hozzá
    -1.33
    مقاله
    -1.33
    POSITIVE LOGITS
     our
    1.88
     we
    1.73
    :
    1.66
     industries
    1.61
     in
    1.58
     sectors
    1.54
    ,
    1.54
     industrial
    1.53
     economic
    1.48
     if
    1.48
    Activations Density 0.018%

    No Known Activations