© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108130
    Prev
    Next
    INDEX
    Explanations

    SAML assertions and federation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    чил
    -0.86
    vande
    -0.83
    endian
    -0.81
     nadzieję
    -0.77
     supervisor
    -0.76
    linha
    -0.73
     الشعر
    -0.73
    nezeu
    -0.73
    vpc
    -0.72
     amarillas
    -0.72
    POSITIVE LOGITS
     SAM
    1.32
    SAM
    1.25
     federation
    1.22
     SSO
    1.15
     feder
    1.15
     SLO
    1.09
     Assertion
    0.98
     relying
    0.94
     asserting
    0.93
    assert
    0.91
    Activations Density 0.048%

    No Known Activations