© 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. 58455
    Prev
    Next
    INDEX
    Explanations

    database context

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

    The neuron detects occurrences of the identifier “db” (in imports, variable names, and method calls) in code.

    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
     ähnliche
    -1.10
     Mittelalter
    -0.92
     furthermore
    -0.91
     diejenigen
    -0.91
    Конечно
    -0.90
     bekannten
    -0.89
     slated
    -0.89
     자신
    -0.88
     übri
    -0.87
    的过程中
    -0.87
    POSITIVE LOGITS
     SILVA
    0.99
    نگی
    0.98
     Schen
    0.97
    uberge
    0.94
     sayur
    0.94
     saya
    0.93
    狮
    0.93
    Ŷ
    0.92
     connection
    0.91
     milj
    0.91
    Activations Density 0.017%

    No Known Activations