© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    programming imports and annotations

    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
     for
    -0.94
     through
    -0.94
    幇
    -0.91
     though
    -0.85
    thresh
    -0.84
    ضى
    -0.82
     hope
    -0.81
     but
    -0.80
     rẻ
    -0.79
    CAPITULO
    -0.79
    POSITIVE LOGITS
     "@
    1.01
    絝
    0.95
    Kuro
    0.87
    Igor
    0.84
    remover
    0.82
    ană
    0.80
     椅子
    0.79
    注解
    0.79
    ">[
    0.79
    
    0.79
    Activations Density 0.010%

    No Known Activations