© 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. 127220
    Prev
    Next
    INDEX
    Explanations

    authentication and authorization

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

    The neuron strongly activates on any token or identifier containing the substring “auth,” i.e. authentication-related 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
    縢
    -1.98
    ors
    -1.77
    莚
    -1.74
    ’，
    -1.72
     Anſ
    -1.70
     was
    -1.67
    絎
    -1.65
     美甲
    -1.63
     باسلام
    -1.63
    оргаш
    -1.63
    POSITIVE LOGITS
    瀦
    2.17
    จาก
    1.94
    cinoma
    1.73
    A
    1.72
     a
    1.68
     deciding
    1.66
    }
    1.62
     Início
    1.62
     nearby
    1.61
    şört
    1.56
    Activations Density 0.021%

    No Known Activations