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. 8134
    Prev
    Next
    INDEX
    Explanations

    compression and hops

    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
     Seok
    -0.74
     ஊ
    -0.74
    ุ่น
    -0.71
     DAK
    -0.71
     Wheat
    -0.71
     Lithium
    -0.71
     joan
    -0.71
     Michaelis
    -0.71
    ้อม
    -0.70
     FETCH
    -0.69
    POSITIVE LOGITS
     hop
    1.11
     hops
    1.09
    hops
    0.96
    Hop
    0.90
     pellets
    0.90
     isomer
    0.88
     whirlpool
    0.87
     cones
    0.82
     cone
    0.80
     hopped
    0.79
    Activations Density 0.008%

    No Known Activations