© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40593
    Prev
    Next
    INDEX
    Explanations

    court documents | legal proceedings

    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_10/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
    With
    -2.97
    After
    -2.83
    想
    -2.78
     With
    -2.67
    漫畫
    -2.61
    由於
    -2.58
    Despite
    -2.56
    During
    -2.53
    2
    -2.53
    Since
    -2.52
    POSITIVE LOGITS
    鸶
    3.86
    襌
    2.84
    
    2.83
    汭
    2.83
    鸸
    2.81
    すすめ
    2.75
    ⚣
    2.72
    튿
    2.70
    
    2.70
    
    2.69
    Activations Density 0.080%

    No Known Activations