© 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. 42475
    Prev
    Next
    INDEX
    Explanations

    quit

    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
    
    -3.00
     presentan
    -2.75
    鹋
    -2.69
     “
    -2.67
    jenigen
    -2.67
     trabalho
    -2.64
     astute
    -2.63
     preço
    -2.63
     nascent
    -2.59
     Ähn
    -2.58
    POSITIVE LOGITS
     стоковые
    2.84
    镦
    2.83
     itſelf
    2.77
    
    2.73
    芣
    2.73
     复古
    2.67
    采用了
    2.61
     fédé
    2.61
     車場
    2.59
    
    2.55
    Activations Density 0.003%

    No Known Activations