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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8521
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    ّة
    -0.85
     encarga
    -0.85
    brać
    -0.84
    wijk
    -0.79
     renfer
    -0.78
    
    -0.77
     墙
    -0.76
     功能
    -0.76
    AKO
    -0.75
    ⟪
    -0.74
    POSITIVE LOGITS
     and
    1.05
    キュー
    0.79
     --
    0.78
    ួ
    0.76
     Tue
    0.75
     files
    0.74
     origin
    0.73
     miesięcy
    0.73
    宿舍
    0.69
    ีม
    0.69
    Activations Density 0.053%

    No Known Activations