© 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. 39977
    Prev
    Next
    INDEX
    Explanations

    programming keywords and definitions

    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
    
    -1.77
     tênis
    -1.63
    컹
    -1.59
     ekonom
    -1.55
     Američ
    -1.54
     tunik
    -1.53
     pneus
    -1.52
     hisz
    -1.52
     wondrous
    -1.52
     唯美
    -1.52
    POSITIVE LOGITS
     just
    1.92
     can
    1.75
     only
    1.70
     to
    1.63
     gets
    1.57
     not
    1.55
    C
    1.54
     Just
    1.53
     does
    1.52
     because
    1.51
    Activations Density 0.088%

    No Known Activations