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. 8080
    Prev
    Next
    INDEX
    Explanations

    words starting with "Sty"

    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
     stopping
    -0.85
    偲
    -0.81
     viciss
    -0.79
     vài
    -0.79
     stockholm
    -0.78
     fua
    -0.77
     differs
    -0.76
     Verge
    -0.74
     sovere
    -0.74
    HTT
    -0.74
    POSITIVE LOGITS
     Sty
    1.32
    Sty
    1.13
     sty
    1.04
    tifying
    0.91
    conscious
    0.84
    ♉
    0.80
    sty
    0.78
     topik
    0.75
     utom
    0.75
    styl
    0.74
    Activations Density 0.009%

    No Known Activations