© 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. 80684
    Prev
    Next
    INDEX
    Explanations

    taken to hospital

    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
     fullt
    -1.66
    และ
    -1.61
     และ
    -1.56
     totalt
    -1.55
     resten
    -1.55
     behand
    -1.54
    ∎
    -1.52
    
    -1.51
    <i>
    -1.51
    olving
    -1.50
    POSITIVE LOGITS
     by
    2.47
     to
    2.25
     two
    2.00
     only
    1.95
     like
    1.80
     using
    1.72
     after
    1.70
     without
    1.70
     in
    1.70
     had
    1.63
    Activations Density 0.018%

    No Known Activations