© 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. 8376
    Prev
    Next
    INDEX
    Explanations

    night or nights

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

    night time

    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
    胝
    0.39
    েষ
    0.38
    ading
    0.35
    โมง
    0.35
     органы
    0.35
    quear
    0.34
    綸
    0.34
     মাঝামা
    0.34
     দের
    0.34
     ತಾ
    0.34
    POSITIVE LOGITS
     night
    4.44
     Night
    4.22
    Night
    4.19
    night
    4.13
     NIGHT
    4.06
    夜
    3.91
     nights
    3.59
     Nacht
    3.39
     नाइट
    3.39
     夜
    3.34
    Activations Density 0.244%

    No Known Activations