© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113940
    Prev
    Next
    INDEX
    Explanations

    antibacterial effects and properties

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

    This neuron detects the term "antibacterial" in scientific and medical contexts.

    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
    -
    -2.33
     The
    -2.28
     Any
    -2.28
     multitudes
    -2.22
     Reihen
    -2.16
    x
    -2.16
     grüne
    -2.14
     aktuell
    -2.14
     Füßen
    -2.09
     Why
    -2.08
    POSITIVE LOGITS
    ⸫
    2.58
    桄
    2.56
     andere
    2.45
     maar
    2.44
    呖
    2.44
     memili
    2.36
    軚
    2.33
     connaissance
    2.33
    峮
    2.31
     biologie
    2.30
    Activations Density 0.002%

    No Known Activations