© 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. 1211
    Prev
    Next
    INDEX
    Explanations

    special noun

    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
     embreagem
    -1.38
     saludables
    -1.34
     traditionnelle
    -1.34
    腱
    -1.34
     étan
    -1.32
     منذ
    -1.30
     depuis
    -1.29
     bekämp
    -1.27
    droj
    -1.26
     aktuell
    -1.26
    POSITIVE LOGITS
     special
    2.20
    special
    2.13
     they
    1.78
     speciale
    1.77
     Special
    1.76
    特别的
    1.74
     специальные
    1.70
    Special
    1.68
     especial
    1.63
     will
    1.59
    Activations Density 0.054%

    No Known Activations