© 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. 10-GEMMASCOPE-RES-131K
    7. 123519
    Prev
    Next
    INDEX
    Explanations

    questions about relative order or magnitude

    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_10/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
    brać
    -1.56
    劻
    -1.55
    넋
    -1.54
     a
    -1.51
     started
    -1.48
    🧩
    -1.46
    ̆
    -1.45
     arī
    -1.41
    asiswa
    -1.39
    gefunden
    -1.38
    POSITIVE LOGITS
     fazendo
    2.03
     таких
    1.92
     remarkably
    1.84
    how
    1.77
    もともと
    1.73
     enfati
    1.70
     exceptionally
    1.67
     Melhor
    1.66
     crucial
    1.66
     dando
    1.66
    Activations Density 0.035%

    No Known Activations