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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7970
    Prev
    Next
    INDEX
    Explanations

    Staphylococcus aureus bacterium

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

    The neuron identifies names of bacteria and countries/locations, particularly Staphylococcus aureus and geographic entities.

    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_10/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
    u
    -3.97
    or
    -3.84
    as
    -3.34
     we
    -3.05
    咐
    -2.69
    o
    -2.67
     that
    -2.52
     desolate
    -2.50
    ISTOL
    -2.50
     When
    -2.42
    POSITIVE LOGITS
    The
    3.48
    １
    2.97
    芣
    2.81
     сделали
    2.73
    なんだか
    2.70
    超過
    2.67
    There
    2.59
    もちろん
    2.58
    It
    2.52
     сказали
    2.52
    Activations Density 0.025%

    No Known Activations