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. 8187
    Prev
    Next
    INDEX
    Explanations

    places, names, identification

    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
    btnNew
    -0.80
     促销
    -0.72
     communi
    -0.72
     актри
    -0.71
    Cancelar
    -0.71
    CULTURE
    -0.69
    韆
    -0.69
     놀
    -0.69
    btnClose
    -0.69
    cja
    -0.68
    POSITIVE LOGITS
    reson
    0.84
    dataIndex
    0.81
     siege
    0.75
    topping
    0.74
    bev
    0.72
    Resolve
    0.71
    憔
    0.70
    ранее
    0.69
    нак
    0.69
    дца
    0.69
    Activations Density 0.023%

    No Known Activations