© 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. 117641
    Prev
    Next
    INDEX
    Explanations

    interface or Service suffixes

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

    The neuron strongly activates on Java/C# type identifiers (class or interface names), especially CamelCase names like Mapper, Service, Repository, Interface, and JpaRepository.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    DaoImpl
    -1.50
    ServiceImpl
    -1.48
     implements
    -1.34
    DAOImpl
    -1.25
     implementation
    -1.13
     implementing
    -1.12
     Implements
    -1.07
    IMPLEMENT
    -0.98
    Implementing
    -0.95
     implement
    -0.93
    POSITIVE LOGITS
     interface
    0.93
    capable
    0.93
    Setiap
    0.91
    OrBuilder
    0.88
    DialogInterface
    0.85
    kort
    0.85
    interface
    0.84
    callbacks
    0.84
    abilit
    0.83
     capable
    0.82
    Activations Density 0.014%

    No Known Activations