© 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. 65702
    Prev
    Next
    INDEX
    Explanations

    really or truly preceding a word

    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
     également
    -1.45
     nuevamente
    -1.28
     as
    -1.27
    ЦИИ
    -1.24
    Опис
    -1.24
     ebenfalls
    -1.22
    不已
    -1.20
     рассказать
    -1.20
    Тарих
    -1.20
    기도
    -1.19
    POSITIVE LOGITS
    ↵
    1.45
     which
    1.39
    »),
    1.38
     significativo
    1.34
     can
    1.31
     endast
    1.27
     sincero
    1.25
     only
    1.24
    langkah
    1.23
    šní
    1.23
    Activations Density 0.073%

    No Known Activations