© 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. 104459
    Prev
    Next
    INDEX
    Explanations

    Spanish and Russian words, punctuation

    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
     Barron
    -0.82
    ळ
    -0.81
    логия
    -0.80
    laboration
    -0.79
    eará
    -0.79
    ність
    -0.77
    ϫ
    -0.77
     军
    -0.76
     either
    -0.75
     egyes
    -0.75
    POSITIVE LOGITS
     words
    0.85
     注册
    0.79
    ༡
    0.78
     everything
    0.77
     Tutorials
    0.77
    SHUT
    0.77
     gatti
    0.76
     permettre
    0.76
     campeón
    0.76
     kroppen
    0.75
    Activations Density 0.146%

    No Known Activations