© 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. 107834
    Prev
    Next
    INDEX
    Explanations

    Hanukkah and Jewish holidays

    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
     crucifixion
    -0.76
     Ephesians
    -0.76
    kowe
    -0.75
     المياه
    -0.75
     coffin
    -0.73
    conducted
    -0.73
     easter
    -0.72
     Barb
    -0.72
     סס
    -0.71
    gó
    -0.70
    POSITIVE LOGITS
    🕎
    1.32
     menor
    1.14
    gelt
    1.12
     Macca
    1.05
     candles
    1.01
     candle
    1.00
    燭
    0.98
     holiday
    0.97
     dicembre
    0.95
     nightly
    0.94
    Activations Density 0.008%

    No Known Activations