© 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. 34-GEMMASCOPE-RES-131K
    4. 7011
    Prev
    Next
    INDEX
    Explanations

    policy and its contexts

    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
     lavander
    -0.82
    ワイイ
    -0.81
    delle
    -0.79
     have
    -0.78
     necesitas
    -0.73
     schönes
    -0.73
    MB
    -0.73
    航天
    -0.72
     наблю
    -0.71
     alberto
    -0.69
    POSITIVE LOGITS
     Policy
    1.01
     enforced
    0.99
     Policies
    0.98
    "},
    
    0.98
    аа
    0.97
     policy
    0.96
     påvir
    0.95
     Pol
    0.92
     menangkap
    0.91
     برای
    0.90
    Activations Density 0.011%

    No Known Activations