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. 8302
    Prev
    Next
    INDEX
    Explanations

    foreign exchange

    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
    taxa
    -0.93
     European
    -0.83
    larının
    -0.81
    項
    -0.79
     gibts
    -0.78
     combinar
    -0.74
    átka
    -0.73
     desconhe
    -0.73
     کا
    -0.72
     laboral
    -0.71
    POSITIVE LOGITS
    Hilton
    0.76
     veri
    0.73
     Sted
    0.73
     Crea
    0.73
     Lond
    0.72
     tableta
    0.71
    视为
    0.71
     Morality
    0.71
     rarest
    0.71
     Prerequisite
    0.71
    Activations Density 0.022%

    No Known Activations