© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103540
    Prev
    Next
    INDEX
    Explanations

    alloc, shape, pages, Enter

    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
     cou
    -0.89
    멀
    -0.75
     правый
    -0.74
     NPR
    -0.69
    lasia
    -0.69
    折
    -0.69
    вля
    -0.68
    ⌨
    -0.68
     compensated
    -0.67
    Julie
    -0.66
    POSITIVE LOGITS
    atör
    0.79
    ̖
    0.79
    嚓
    0.75
    oxford
    0.75
     Sitemap
    0.75
     государства
    0.73
    ^{*}\
    0.73
     passagem
    0.72
     그것
    0.72
     lamenta
    0.71
    Activations Density 0.009%

    No Known Activations