© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9761
    Prev
    Next
    INDEX
    Explanations

    passwords in code and commands

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

    This neuron activates on code lines defining database connection constants (especially DB_HOST, DB_USER, DB_PASS) and their string assignments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     any
    -1.39
     its
    -1.13
    ==""){
    -1.12
     such
    -1.02
    drawImage
    -0.99
     technologies
    -0.98
    BindingResult
    -0.98
    емов
    -0.96
     strategies
    -0.96
    XmlAttribute
    -0.95
    POSITIVE LOGITS
     vard
    1.04
    creating
    1.00
     lingual
    0.94
     loca
    0.92
     xxxx
    0.91
     aspar
    0.89
    干嘛
    0.88
     formant
    0.88
     goi
    0.88
     recently
    0.87
    Activations Density 0.006%

    No Known Activations