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. 8126
    Prev
    Next
    INDEX
    Explanations

    lefty, Lefrandt, Lefevre, leftists

    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
     oncoming
    -0.76
    役
    -0.74
     الكريم
    -0.73
    腾
    -0.72
     écran
    -0.71
     Overload
    -0.71
    образие
    -0.70
     ニュース
    -0.69
     overload
    -0.69
     maintain
    -0.68
    POSITIVE LOGITS
     სა
    0.88
    hlar
    0.80
    udra
    0.79
    まさか
    0.78
    Elő
    0.77
    olytic
    0.75
     מצ
    0.73
     alugar
    0.71
     hors
    0.70
    だいぶ
    0.69
    Activations Density 0.039%

    No Known Activations