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. 8477
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    NP
    -0.73
     constater
    -0.70
     ап
    -0.68
     अप
    -0.67
    Paste
    -0.65
    Water
    -0.65
    VENTORY
    -0.65
     imig
    -0.64
     wap
    -0.64
     internationale
    -0.64
    POSITIVE LOGITS
     Chiang
    0.75
    ẳ
    0.69
     recommandée
    0.69
    Mitochond
    0.69
     vieron
    0.69
     Aig
    0.69
     वृ
    0.68
    Chili
    0.68
    テーション
    0.67
     Mitochondrial
    0.66
    Activations Density 0.062%

    No Known Activations