© 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. 19558
    Prev
    Next
    INDEX
    Explanations

    words ending in 's'

    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
     bruin
    -1.82
    neling
    -1.73
     civils
    -1.72
    ïde
    -1.70
    thodon
    -1.69
     herbes
    -1.68
    ilets
    -1.66
    kování
    -1.65
     forment
    -1.63
    uuuu
    -1.61
    POSITIVE LOGITS
    ↵↵
    2.02
     factors
    1.91
     you
    1.89
     regulations
    1.84
     conditions
    1.73
     rules
    1.73
     elements
    1.72
     if
    1.69
     features
    1.68
     individuals
    1.63
    Activations Density 0.048%

    No Known Activations