© 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. 1095
    Prev
    Next
    INDEX
    Explanations

    economic growth

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

    economic growth and stability

    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
    纹
    0.48
    Benzyloxy
    0.41
    协助
    0.41
     Notification
    0.40
    书法
    0.40
     notificación
    0.40
    样品
    0.40
     Frequency
    0.39
     请
    0.39
    辂
    0.39
    POSITIVE LOGITS
    經濟
    1.03
    economic
    0.98
     економі
    0.93
     economic
    0.91
    経済
    0.90
     macroeconomic
    0.88
     ECONOMIC
    0.87
     경제
    0.87
     экономики
    0.85
     اقتصاد
    0.85
    Activations Density 0.399%

    No Known Activations