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. 8554
    Prev
    Next
    INDEX
    Explanations

    may, margin, work

    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
    sApp
    -0.81
    ikiki
    -0.80
     rul
    -0.70
    됐
    -0.69
     liệu
    -0.69
    authority
    -0.69
    mie
    -0.68
    товано
    -0.68
    ,{\
    -0.68
     &___
    -0.68
    POSITIVE LOGITS
     Everyone
    0.81
    Everyone
    0.79
    ξεις
    0.78
     perish
    0.78
    šas
    0.77
     ANN
    0.77
     gancho
    0.75
    רקע
    0.74
    扩展
    0.74
    Kö
    0.74
    Activations Density 0.005%

    No Known Activations