© 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. 104193
    Prev
    Next
    INDEX
    Explanations

    two-factor authentication MFA

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

    the acronym "MFA" (Master of Fine Arts) or references to two-factor authentication.

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

    This neuron detects mentions of two-factor (or multi-factor) authentication—e.g. “two-factor authentication,” “2-FA,” etc.

    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
    IANGLES
    -1.56
    
    -1.55
    寕
    -1.51
    或者
    -1.47
    linawan
    -1.41
    直至
    -1.40
     что
    -1.38
    ingeki
    -1.38
     écoles
    -1.37
    concep
    -1.37
    POSITIVE LOGITS
    ”（
    1.52
    ınıza
    1.51
     女の子
    1.51
    
    1.48
     appellate
    1.48
    images
    1.47
    uellement
    1.46
     achieve
    1.45
    getInteger
    1.45
     their
    1.41
    Activations Density 0.007%

    No Known Activations