© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84695
    Prev
    Next
    INDEX
    Explanations

    oauth 2.0 or refresh token

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

    The neuron fires on occurrences of the term “OAuth” (especially “OAuth 2”) in the text.

    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
     That
    -3.48
    1
    -2.70
    脔
    -2.66
    i
    -2.64
    佧
    -2.42
     But
    -2.41
    crania
    -2.39
     By
    -2.36
     Of
    -2.36
     So
    -2.34
    POSITIVE LOGITS
    s
    3.53
    '
    3.38
     henne
    2.38
    wwww
    2.27
     WARS
    2.20
    鱟
    2.20
    Ⓡ
    2.17
    wwwww
    2.14
     LUNCH
    2.14
     LOCATION
    2.13
    Activations Density 0.001%

    No Known Activations