© 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. 30051
    Prev
    Next
    INDEX
    Explanations

    stock market and trading

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

    The neuron detects stock‐market and equity‐related terms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Hearts
    -0.76
     黑色
    -0.75
    Stocks
    -0.73
     francês
    -0.72
    女孩子
    -0.71
    essége
    -0.70
     Gathering
    -0.70
    AIL
    -0.69
     绘画
    -0.69
    优化
    -0.69
    POSITIVE LOGITS
     prices
    1.16
     price
    1.09
     ownership
    0.85
     Ownership
    0.85
     selection
    0.84
    roveň
    0.84
    Topology
    0.83
     τι
    0.83
     Freiheit
    0.82
    LoginActivity
    0.82
    Activations Density 0.015%

    No Known Activations