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. 8418
    Prev
    Next
    INDEX
    Explanations

    part of, for, or with

    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
    櫃
    -0.85
    Filosof
    -0.79
    roben
    -0.79
    Seni
    -0.77
    ❇
    -0.77
    смарт
    -0.76
    Rote
    -0.74
    Escu
    -0.73
    Vee
    -0.72
    Proses
    -0.72
    POSITIVE LOGITS
    barrel
    0.90
     clang
    0.86
     turnover
    0.86
    행
    0.85
    lė
    0.81
    clang
    0.81
     номина
    0.79
    Ḫ
    0.77
     управление
    0.76
    оло
    0.74
    Activations Density 0.018%

    No Known Activations