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. 8395
    Prev
    Next
    INDEX
    Explanations

    mutagenicity tests on cells

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

    scientific terminology related to genetic mutations and DNA testing.

    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
    FLOAT
    -0.75
     lyss
    -0.73
    setAction
    -0.72
    lyte
    -0.72
     TERM
    -0.71
    TRIM
    -0.71
    術
    -0.71
     monog
    -0.70
     isinstance
    -0.70
     Bites
    -0.69
    POSITIVE LOGITS
     mutagenicity
    1.23
     Mutation
    1.02
     muta
    1.01
     mutation
    0.99
    Mutation
    0.93
    Ames
    0.93
     detects
    0.90
     Ames
    0.90
    AMES
    0.89
    护士
    0.86
    Activations Density 0.149%

    No Known Activations