© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75985
    Prev
    Next
    INDEX
    Explanations

    bacterial strains

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

    This neuron identifies scientific names of bacteria and microorganisms, especially at the end of genus-species names.

    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
    村
    -0.80
    TRACK
    -0.80
    ⋙
    -0.79
     Fusarium
    -0.78
    档
    -0.78
    ون
    -0.74
    Ингредиенты
    -0.73
     fino
    -0.73
    getSeconds
    -0.72
    teu
    -0.72
    POSITIVE LOGITS
     strain
    2.17
     strains
    1.84
    strain
    1.54
     Strains
    1.48
    Strain
    1.48
     Strain
    1.46
    strains
    1.31
    ATCC
    1.15
     isolate
    0.89
    株
    0.89
    Activations Density 0.221%

    No Known Activations