© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45775
    Prev
    Next
    INDEX
    Explanations

    economy and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     efectivos
    0.64
    م
    0.54
    ر
    0.54
     கம்ப
    0.52
    Lr
    0.51
    M
    0.51
    er
    0.50
    alek
    0.50
    ె
    0.50
    D
    0.49
    POSITIVE LOGITS
     ekonomi
    1.16
     economic
    1.05
     économ
    1.05
     économique
    1.03
     economica
    1.02
     economici
    1.01
     ECONOMIC
    1.00
     экономи
    0.99
    economic
    0.99
    经济
    0.97
    Activations Density 0.034%

    No Known Activations