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. 124
    Prev
    Next
    INDEX
    Explanations

    This is a part

    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
     lady
    -0.81
     what
    -0.79
     tending
    -0.79
    負担
    -0.79
     предме
    -0.79
     pseud
    -0.78
     Drogen
    -0.77
     capability
    -0.76
     loading
    -0.75
     coolest
    -0.75
    POSITIVE LOGITS
    Ẻ
    0.95
    ϰ
    0.79
    為に
    0.77
    ̀ng
    0.76
     questões
    0.75
    depor
    0.75
    sí
    0.74
     Helens
    0.74
    änd
    0.73
    wohner
    0.73
    Activations Density 0.006%

    No Known Activations