© 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. 22-GEMMASCOPE-RES-131K
    4. 9726
    Prev
    Next
    INDEX
    Explanations

    or, either/or

    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
     declarat
    -1.37
    และ
    -1.35
     maxime
    -1.32
     MATER
    -1.27
     fournisseurs
    -1.26
    
    -1.23
     riu
    -1.19
     Rè
    -1.19
     astronom
    -1.18
     própri
    -1.17
    POSITIVE LOGITS
     or
    4.03
     или
    1.98
     any
    1.94
     may
    1.86
     if
    1.86
    或是
    1.69
     at
    1.68
     either
    1.66
    或者是
    1.63
     либо
    1.59
    Activations Density 0.180%

    No Known Activations