© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98248
    Prev
    Next
    INDEX
    Explanations

    SAML, Q:, 1

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

    This neuron detects technical references to SAML authentication payloads—especially “SAML response” and “NameID” elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Musée
    -0.82
     violation
    -0.81
     Violation
    -0.79
    lective
    -0.75
    gula
    -0.75
    ึ้น
    -0.75
    Violation
    -0.74
    cassert
    -0.70
     preamble
    -0.69
    herit
    -0.69
    POSITIVE LOGITS
     piezoelectric
    0.77
    urium
    0.75
    闔
    0.72
     DataType
    0.70
     piezo
    0.68
    &)
    0.68
    oost
    0.68
     weary
    0.67
    スレ
    0.67
    getPassword
    0.67
    Activations Density 0.010%

    No Known Activations