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. 80
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    และ
    -0.93
     savu
    -0.91
     erzeugt
    -0.87
     rendre
    -0.86
    produit
    -0.85
     петербург
    -0.84
     bezw
    -0.84
    家で
    -0.83
     мужчин
    -0.82
    ouc
    -0.82
    POSITIVE LOGITS
     remun
    1.17
     Normally
    1.11
    ၟ
    1.09
     susten
    1.06
     cerim
    1.05
     quiso
    1.03
    Хотя
    1.03
     locomo
    1.02
     rudimentary
    1.02
     Obviously
    1.01
    Activations Density 0.038%

    No Known Activations