© 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. 34-GEMMASCOPE-RES-131K
    7. 58790
    Prev
    Next
    INDEX
    Explanations

    access permissionsrightsauthorization

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

    The neuron detects access‐control and permission terminology, especially phrases indicating a user has or lacks access.

    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
     comté
    -0.88
    ClInclude
    -0.83
    五行
    -0.78
    toBeTruthy
    -0.76
     championnat
    -0.75
    ਦੇ
    -0.75
    sociation
    -0.75
    UniqueId
    -0.74
    เตอร์
    -0.73
     ज्ञात
    -0.72
    POSITIVE LOGITS
     permissions
    3.52
     permission
    3.36
    权限
    2.92
    permissions
    2.69
     Permission
    2.61
    permission
    2.58
    Permission
    2.55
    Permissions
    2.47
     Permissions
    2.44
     rights
    2.39
    Activations Density 0.146%

    No Known Activations