Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7866
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry and chemical units

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific notation and chemical formulas in technical or academic texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Devonian
    -0.91
     überprü
    -0.85
    選擇
    -0.83
     häls
    -0.83
     Byzantium
    -0.82
     Snowman
    -0.81
     gelten
    -0.80
    opel
    -0.80
     innych
    -0.80
     veggie
    -0.79
    POSITIVE LOGITS
     Za
    0.77
    sedown
    0.75
     gerak
    0.73
    creatic
    0.72
    孤立
    0.72
     Kugel
    0.72
     maand
    0.71
    drone
    0.71
    SuppressWarnings
    0.71
     Jahre
    0.71
    Activations Density 0.001%

    No Known Activations