© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4090
    Prev
    Next
    INDEX
    Explanations

    urban sanitation and enterprise

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

    creating an enabling environment

    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_53_width_65k_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
     grosseur
    0.62
    将军
    0.61
     caucasian
    0.58
    总裁
    0.58
    咱们
    0.57
    战士
    0.57
    贾
    0.57
    玛
    0.57
    开心
    0.57
     भक्तों
    0.57
    POSITIVE LOGITS
     livelihoods
    1.01
     linkages
    0.91
     sectoral
    0.89
     UNDP
    0.86
     fuelwood
    0.86
     WASH
    0.85
     USAID
    0.81
     informal
    0.81
     livelihood
    0.80
     governance
    0.79
    Activations Density 0.145%

    No Known Activations