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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3036
    Prev
    Next
    INDEX
    Explanations

    views and scenery

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

    scenic panoramas and views

    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
     burdensome
    0.47
     اتباع
    0.45
     sinnvoll
    0.43
    蒻
    0.43
    ẩu
    0.42
     যাচাই
    0.41
     নির্ভরযোগ্য
    0.41
     makalah
    0.41
    铤
    0.41
     مفید
    0.40
    POSITIVE LOGITS
    景色
    2.09
     panorama
    2.03
     scenery
    2.03
     panor
    2.02
     panoramic
    1.99
     vistas
    1.88
    風景
    1.77
     panoram
    1.75
    风景
    1.74
     views
    1.71
    Activations Density 0.397%

    No Known Activations