© 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. 10-GEMMASCOPE-RES-131K
    7. 130255
    Prev
    Next
    INDEX
    Explanations

    password fields, database credentials

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

    The neuron activates on occurrences of “password” (and related password‐field tokens) in code or schema.

    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
     kuni
    -2.02
     \_
    -1.70
     anuncia
    -1.67
    
    -1.66
     naturen
    -1.63
     あります
    -1.60
     kazak
    -1.59
     variété
    -1.59
     abiye
    -1.55
    щей
    -1.54
    POSITIVE LOGITS
     등
    1.47
    raires
    1.45
     Estamos
    1.43
     after
    1.40
     Ironically
    1.39
     Institutionen
    1.38
    ioterapia
    1.38
     Antrags
    1.37
     time
    1.36
     February
    1.36
    Activations Density 0.015%

    No Known Activations