© 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. 34-GEMMASCOPE-RES-131K
    7. 60811
    Prev
    Next
    INDEX
    Explanations

    New Year celebrations

    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_34/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
    圣诞
    -0.91
    Halloween
    -0.91
    聖誕
    -0.90
    źni
    -0.84
    国庆
    -0.82
    foundland
    -0.79
    sieurs
    -0.79
    clav
    -0.79
    Ec
    -0.77
    Ճ
    -0.77
    POSITIVE LOGITS
     тради
    1.20
     tradition
    1.16
     Year
    1.09
     trady
    1.09
     Lunar
    1.04
     festive
    1.02
     auspicious
    1.02
     traditional
    1.02
     New
    1.02
    traditional
    1.00
    Activations Density 0.016%

    No Known Activations