© 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. 22-GEMMASCOPE-RES-131K
    7. 9517
    Prev
    Next
    INDEX
    Explanations

    words ending in ai

    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_22/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
     in
    -2.84
    ↵↵
    -2.80
     '',
    -2.64
    a
    -2.61
     ,
    -2.59
     eight
    -2.58
     September
    -2.55
    \
    -2.52
     six
    -2.52
     nueva
    -2.48
    POSITIVE LOGITS
     constitue
    3.09
    
    3.03
     hadde
    3.00
    瑁
    2.86
    
    2.86
     contribue
    2.84
     Autó
    2.75
    ╽
    2.75
     tesettür
    2.63
    硨
    2.61
    Activations Density 0.103%

    No Known Activations