© 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. 71537
    Prev
    Next
    INDEX
    Explanations

    superlative descriptors

    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
     everything
    -0.97
     all
    -0.93
     every
    -0.92
     such
    -0.90
     mají
    -0.88
     太郎
    -0.82
    vää
    -0.82
    ladiator
    -0.79
     wisdom
    -0.79
    Their
    -0.77
    POSITIVE LOGITS
     hopefully
    1.80
    hopefully
    1.57
     Hopefully
    1.52
    Hopefully
    1.42
     благодаря
    1.00
     abbastanza
    0.99
     برخی
    0.98
    的一些
    0.96
     (%)
    0.92
    つもり
    0.91
    Activations Density 0.061%

    No Known Activations