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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31746
    Prev
    Next
    INDEX
    Explanations

    Christmas events and traditions

    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
     autumn
    -1.05
    嫆
    -0.98
     valentines
    -0.95
     valentine
    -0.92
    genodigd
    -0.91
     responsabilità
    -0.91
     Layanan
    -0.91
     Sucher
    -0.91
     tertentu
    -0.90
    こちらが
    -0.90
    POSITIVE LOGITS
     Eve
    1.41
    time
    1.41
     season
    0.98
     Carol
    0.96
     утром
    0.94
    Eve
    0.90
     Morning
    0.90
    濠
    0.89
    中学
    0.89
     Present
    0.87
    Activations Density 0.011%

    No Known Activations