© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104629
    Prev
    Next
    INDEX
    Explanations

    Sarawak, DbContext, SaveChanges, Unmount, HMS

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

    references to DbContext in programming code, particularly in Entity Framework and database-related technical discussions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on C# identifier tokens—especially CamelCase class and method names (e.g. DbContext, SaveChanges, UnitOfWork, PropertyChanging).

    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
    淠
    -2.50
    ."
    -2.39
    ांकि
    -2.25
    鸶
    -2.23
    无疑
    -2.23
    勦
    -2.19
    鹮
    -2.16
    瑨
    -2.16
     могут
    -2.13
    旆
    -2.13
    POSITIVE LOGITS
    みたら
    2.20
    独自
    2.14
    ());
    2.14
    蕷
    2.11
    にい
    2.06
     Use
    2.05
     réservé
    2.02
    lgari
    2.02
     теме
    1.99
     Replacing
    1.98
    Activations Density 0.001%

    No Known Activations