© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12397
    Prev
    Next
    INDEX
    Explanations

    sale of commodities

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

    commodity prices, exports, hedging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    恐惧
    0.89
    娇
    0.89
    狱
    0.85
    诒
    0.84
     تعلیم
    0.84
    神经
    0.80
    欤
    0.80
    鹘
    0.80
    瓒
    0.80
    讽
    0.79
    POSITIVE LOGITS
     export
    1.27
     exporters
    1.24
     shipments
    1.19
    export
    1.16
     exported
    1.16
     exporter
    1.16
     exports
    1.15
     growers
    1.10
     shipment
    1.09
     shippers
    1.07
    Activations Density 0.119%

    No Known Activations