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. 8232
    Prev
    Next
    INDEX
    Explanations

    Williams syndrome

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

    proper nouns, particularly place names and educational institutions.

    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
     node
    -0.81
     accomplishment
    -0.78
     Fast
    -0.73
     Friedhof
    -0.73
    coran
    -0.72
    fast
    -0.71
     Ali
    -0.69
     command
    -0.69
     Gil
    -0.68
    左手
    -0.68
    POSITIVE LOGITS
     Williamsburg
    1.88
     williams
    1.15
    Williams
    0.97
    williams
    0.87
     WY
    0.86
    freundlich
    0.81
     wm
    0.81
    zucht
    0.80
    Replication
    0.77
    КО
    0.76
    Activations Density 0.027%

    No Known Activations