© 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. 62682
    Prev
    Next
    INDEX
    Explanations

    market analysis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    álna
    -0.93
    NSDate
    -0.87
    ³,
    -0.82
    uyên
    -0.81
    eBay
    -0.81
     İl
    -0.79
     mudar
    -0.79
     במח
    -0.79
     exclusively
    -0.78
     офі
    -0.77
    POSITIVE LOGITS
     market
    2.91
     Market
    2.13
    Market
    1.89
    market
    1.83
     markets
    1.75
    市場
    1.73
    市场
    1.66
     global
    1.61
    MARKET
    1.57
     mercado
    1.53
    Activations Density 0.014%

    No Known Activations