© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    staff, service, ordering

    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
    üksek
    -1.01
    就可以了
    -0.92
      
    -0.91
     echa
    -0.89
    
    -0.87
     []:
    -0.85
    ↵↵↵↵↵
    -0.84
    勋
    -0.84
     испы
    -0.84
     [
    -0.83
    POSITIVE LOGITS
     waitress
    1.23
     waiter
    1.13
    )$/,
    1.05
    /*",
    1.02
     staff
    1.02
     テーブル
    1.00
    ující
    1.00
    áme
    1.00
    私たちの
    0.99
     bestellen
    0.98
    Activations Density 0.002%

    No Known Activations