© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70633
    Prev
    Next
    INDEX
    Explanations

    night time activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下午
    -0.96
    Today
    -0.91
     Seminary
    -0.88
     วัน
    -0.88
    今天
    -0.88
    پار
    -0.86
    paro
    -0.85
     dynamic
    -0.85
     blom
    -0.85
    võ
    -0.85
    POSITIVE LOGITS
     night
    1.56
     nocturnal
    1.48
     sleep
    1.28
     overnight
    1.28
     nighttime
    1.27
     nights
    1.26
     Night
    1.22
     midnight
    1.16
     that
    1.13
     đêm
    1.10
    Activations Density 0.003%

    No Known Activations