© 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. 110506
    Prev
    Next
    INDEX
    Explanations

    password, username, credentials

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

    database connection credentials and parameters, particularly usernames and passwords in configuration code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on database connection credential tokens (e.g. host, user, password, database names).

    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
     eficaz
    -1.48
     soltar
    -1.38
     his
    -1.36
     semanal
    -1.36
     Японии
    -1.34
     nowej
    -1.30
     związane
    -1.28
     dotyczą
    -1.28
     aumentando
    -1.27
    hankelijk
    -1.26
    POSITIVE LOGITS
     dialami
    1.33
    erdings
    1.27
    Merkmale
    1.16
     meninggal
    1.14
     forze
    1.13
    蹿
    1.13
     pagine
    1.13
     olacaktır
    1.12
     discernible
    1.11
     високо
    1.09
    Activations Density 0.072%

    No Known Activations