© 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. 22-GEMMASCOPE-RES-131K
    4. 389
    Prev
    Next
    INDEX
    Explanations

    current user

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

    This neuron detects references to the current authenticated user (e.g. “current_user,” authentication checks, user-id retrieval).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    외부
    -1.16
     and
    -1.14
     new
    -1.00
    TONY
    -0.98
     lump
    -0.96
     Politiker
    -0.96
     tenido
    -0.96
     sections
    -0.94
     Vereinig
    -0.93
     each
    -0.93
    POSITIVE LOGITS
     selaku
    1.15
     {$\
    1.02
    這是
    0.98
    ゴ
    0.97
    ああ
    0.93
    有個
    0.93
    わたしは
    0.93
     Boletín
    0.91
     déplacements
    0.91
    assemblée
    0.88
    Activations Density 0.008%

    No Known Activations