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. 8501
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or code paths

    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
     layout
    -0.81
    Layout
    -0.73
    ODES
    -0.73
     Ве
    -0.72
     Flint
    -0.71
     Webb
    -0.71
    adra
    -0.71
    ellery
    -0.71
     ilość
    -0.69
    ardino
    -0.68
    POSITIVE LOGITS
    byl
    0.73
     oranges
    0.70
     cerdo
    0.65
    一来
    0.64
     пони
    0.62
    ۗ
    0.62
     orange
    0.61
    ajo
    0.61
    annya
    0.60
     overridden
    0.60
    Activations Density 0.064%

    No Known Activations