Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8001
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

    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_34/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
    менение
    -1.29
     acrylique
    -1.19
     küche
    -1.14
    formación
    -1.12
     teórico
    -1.11
    なのかな
    -1.11
     šed
    -1.10
     eficientes
    -1.10
    だと思う
    -1.05
    なのでしょう
    -1.05
    POSITIVE LOGITS
     män
    1.36
    でございます
    1.25
    These
    1.19
    子は
    1.18
    Πηγές
    1.17
     ※
    1.16
    んですか
    1.15
    子さん
    1.12
     pasaran
    1.11
     hän
    1.06
    Activations Density 0.130%

    No Known Activations