© 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. 10-GEMMASCOPE-RES-131K
    7. 130699
    Prev
    Next
    INDEX
    Explanations

    Entity Framework DbSet

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

    The neuron responds strongly to mentions of “Entity”-related API identifiers (e.g. Entity, EntityFramework, DbContext, DbSet).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    罽
    -1.72
    ༷
    -1.68
     dando
    -1.64
    睃
    -1.61
    
    -1.57
    ⓒ
    -1.54
    鸲
    -1.48
    mainly
    -1.45
     \
    -1.43
    氿
    -1.43
    POSITIVE LOGITS
     When
    1.51
    2
    1.48
     What
    1.45
     Also
    1.41
     Extremely
    1.40
     Surprisingly
    1.40
     廠
    1.38
     mutter
    1.37
    Surprisingly
    1.35
     Initially
    1.34
    Activations Density 0.007%

    No Known Activations