© 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. 106442
    Prev
    Next
    INDEX
    Explanations

    economic outlook and market sentiment

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on words that signal economic or financial market conditions (e.g. terms like “economy,” “indicators,” “weaknesses,” “prices,” “trouble,” “havoc,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     essais
    -1.29
    毎年
    -1.27
    sometimes
    -1.27
    often
    -1.21
     włosów
    -1.20
     eficacia
    -1.18
    Identify
    -1.17
     proposto
    -1.16
     festge
    -1.16
     garder
    -1.15
    POSITIVE LOGITS
     macroeconomic
    1.93
     economists
    1.58
     analysts
    1.53
     October
    1.40
     markets
    1.35
     September
    1.34
     February
    1.30
     economic
    1.29
     investors
    1.28
     will
    1.24
    Activations Density 0.069%

    No Known Activations