© 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. 110771
    Prev
    Next
    INDEX
    Explanations

    java query construction and parameters

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

    Java/JPA query-related code, particularly method calls and class references in database query contexts.

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

    The neuron flags programming tokens related to building or running database queries (e.g. “query”/“Query,” “hql,” “JPQL,” “createQuery,” “setParameter,” etc.).

    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
     {
    -1.87
                
    -1.63
    There
    -1.60
     There
    -1.59
                            
    -1.53
    。
    -1.52
    That
    -1.52
              
    -1.48
    These
    -1.47
        
    -1.46
    POSITIVE LOGITS
     вспом
    1.63
     bijzonder
    1.57
     detalladas
    1.45
    镬
    1.41
     swojego
    1.41
     rechercher
    1.41
    kkk
    1.38
     pomocą
    1.38
     bijzondere
    1.34
    >?
    1.32
    Activations Density 0.004%

    No Known Activations