© 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. 69146
    Prev
    Next
    INDEX
    Explanations

    similar code and foreign words

    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
     sporad
    -1.05
    があり
    -1.02
    álise
    -1.00
     as
    -0.99
     most
    -0.98
    を用
    -0.96
    nī
    -0.96
     mostly
    -0.96
     岁
    -0.94
    縉
    -0.94
    POSITIVE LOGITS
     zostać
    1.11
    向けの
    1.05
    ݯ
    1.01
     وزار
    0.99
     nubes
    0.98
    豺
    0.98
     iban
    0.97
               
    0.96
     kanker
    0.96
     olvidado
    0.96
    Activations Density 0.052%

    No Known Activations