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. 8122
    Prev
    Next
    INDEX
    Explanations

    configurations, features, roles

    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
    вшей
    -0.68
    ابعة
    -0.64
     劉
    -0.64
    hime
    -0.64
     entirely
    -0.63
     tenté
    -0.63
    owners
    -0.63
    อยู่ใน
    -0.63
     Merrill
    -0.62
    ImageIO
    -0.62
    POSITIVE LOGITS
    rof
    0.76
     beagle
    0.70
     gypsum
    0.68
    agara
    0.67
    Storia
    0.66
     апте
    0.66
     Replica
    0.65
    Yor
    0.65
    わけではない
    0.64
     carts
    0.64
    Activations Density 0.054%

    No Known Activations