© 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. 10-GEMMASCOPE-RES-131K
    7. 99423
    Prev
    Next
    INDEX
    Explanations

    database connection configuration

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

    The neuron fires strongly on uppercase database configuration tokens (e.g. DB_HOST, DB_USER, DB_PASS, DB_NAME) 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_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
    ulation
    -1.24
     examines
    -1.13
     therefore
    -1.11
     kakao
    -1.09
    ‌تر
    -1.09
    ardians
    -1.09
     reç
    -1.09
    купа
    -1.06
     some
    -1.05
    ERS
    -1.05
    POSITIVE LOGITS
     Gdy
    1.16
    ்கள்
    1.13
    можно
    1.13
     діяльності
    1.04
     Каждый
    1.03
     osten
    1.02
    暈
    1.02
    驭
    1.02
    出来た
    1.02
     by
    1.00
    Activations Density 0.103%

    No Known Activations