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. 8424
    Prev
    Next
    INDEX
    Explanations

    date and tag labels

    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
    FRAG
    -0.96
     BROS
    -0.83
     responded
    -0.76
     rewarding
    -0.76
     unrealistic
    -0.74
     transferred
    -0.73
     insight
    -0.72
     profan
    -0.72
    ungkinan
    -0.72
     改
    -0.71
    POSITIVE LOGITS
     nucle
    0.86
     arché
    0.84
    Mosa
    0.84
    DOCK
    0.82
     homomorphism
    0.80
     összes
    0.80
    專輯
    0.79
    壌
    0.77
    ųjų
    0.77
    ställ
    0.77
    Activations Density 0.011%

    No Known Activations