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. 8469
    Prev
    Next
    INDEX
    Explanations

    microbiology and microbes

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

    text related to microbiology, particularly scientific and academic content about microorganisms.

    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
     insurer
    -0.85
    带
    -0.77
     actuar
    -0.77
     đo
    -0.75
    Legal
    -0.74
    勞
    -0.73
     menjalani
    -0.73
    endaftaran
    -0.73
     exon
    -0.73
    ksiä
    -0.71
    POSITIVE LOGITS
     microbial
    1.28
     ASM
    1.09
     infectious
    1.07
    microb
    1.02
     microbio
    1.02
     Microbial
    1.00
     Microbiology
    1.00
    microbial
    1.00
     Microb
    0.97
     microbes
    0.96
    Activations Density 0.050%

    No Known Activations