© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110900
    Prev
    Next
    INDEX
    Explanations

    Within time units

    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
    apparently
    -1.87
     GETTING
    -1.79
    representing
    -1.78
    providing
    -1.78
    featuring
    -1.75
    allowing
    -1.70
    despite
    -1.69
     MAKING
    -1.67
    commonly
    -1.66
    
    -1.66
    POSITIVE LOGITS
     or
    2.25
     либо
    1.68
     Within
    1.66
     ataupun
    1.62
     ingrained
    1.59
     sizable
    1.57
     sizeable
    1.55
     That
    1.45
     Those
    1.43
    
    1.43
    Activations Density 0.029%

    No Known Activations