© 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. 148149
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms

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

    examples, results, or fixes

    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
     आणि
    0.74
     અને
    0.63
    alarını
    0.56
     și
    0.54
    malı
    0.53
    và
    0.53
    玛
    0.52
    さんと
    0.51
    এবং
    0.51
    滨
    0.51
    POSITIVE LOGITS
     exportation
    0.54
     attainment
    0.53
     remittances
    0.53
     mobilization
    0.52
     increase
    0.50
     tariffs
    0.50
     attaining
    0.49
     undertakings
    0.49
     hijas
    0.48
    ادرات
    0.47
    Activations Density 0.000%

    No Known Activations