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. 8458
    Prev
    Next
    INDEX
    Explanations

    questions about programming and style

    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
    </h1>
    -0.80
     assistants
    -0.78
    Срок
    -0.76
    ємо
    -0.76
    кает
    -0.75
     almost
    -0.75
     immune
    -0.74
     only
    -0.73
     inflammation
    -0.73
    salut
    -0.72
    POSITIVE LOGITS
    臃
    0.82
    打击
    0.77
     auftreten
    0.77
     какой
    0.76
    yant
    0.73
     stator
    0.73
    ->$
    0.73
    küche
    0.72
     дорого
    0.71
     zusammenge
    0.71
    Activations Density 0.000%

    No Known Activations