© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    multilingual verb endings

    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
     this
    -2.22
    ができます
    -2.14
     will
    -2.13
    をします
    -2.02
     it
    -1.90
    It
    -1.90
     would
    -1.80
     could
    -1.80
    が可能
    -1.77
     If
    -1.75
    POSITIVE LOGITS
     luxus
    1.95
     univerz
    1.91
     kré
    1.87
     chè
    1.80
     唯美
    1.80
     to
    1.75
    obviously
    1.74
     maje
    1.73
     kabát
    1.72
     lã
    1.71
    Activations Density 0.012%

    No Known Activations