© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10727
    Prev
    Next
    INDEX
    Explanations

    SQL CASE and aggregate functions

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

    SQL SELECT statements

    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_40_width_16k_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
    譁
    0.50
    朝鮮
    0.42
     Règ
    0.42
     lưu
    0.41
     Delt
    0.38
     dangerously
    0.38
    oczy
    0.38
    বাহ
    0.38
    唳
    0.38
     dynamics
    0.37
    POSITIVE LOGITS
     SUM
    0.88
     DISTINCT
    0.83
     AVG
    0.80
     CASE
    0.75
    SUM
    0.74
     concat
    0.74
    AVG
    0.73
     COUNT
    0.72
    agg
    0.70
     aggregation
    0.70
    Activations Density 0.022%

    No Known Activations