© 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. 10-GEMMASCOPE-RES-131K
    7. 118951
    Prev
    Next
    INDEX
    Explanations

    legal articles and acts

    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
     either
    -1.61
     Their
    -1.52
     because
    -1.49
     themselves
    -1.48
     their
    -1.44
     with
    -1.44
     through
    -1.34
    積み
    -1.27
     они
    -1.25
     They
    -1.24
    POSITIVE LOGITS
     inalámbrica
    1.38
    ↵↵↵
    1.38
     artikkelen
    1.30
    屋さん
    1.27
     means
    1.25
     industriales
    1.24
     نقل
    1.23
    므
    1.23
    ↵
    1.23
    
    1.21
    Activations Density 0.035%

    No Known Activations