© 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. 117949
    Prev
    Next
    INDEX
    Explanations

    drug and antibiotic resistance

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

    references to antimicrobial resistance in medical or scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of “resistance” (especially in drug‐ or pathogen‐resistance contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     démarrer
    -0.91
     Infection
    -0.81
    Infection
    -0.79
     vegano
    -0.78
     courir
    -0.77
    removed
    -0.75
    Семья
    -0.75
     hygien
    -0.75
    τικές
    -0.74
    ctive
    -0.72
    POSITIVE LOGITS
     resistance
    4.06
     resistant
    3.23
     Resistance
    3.19
    resistance
    3.16
    Resistance
    3.08
    resistant
    2.64
     resistances
    2.63
     resistencia
    2.58
     résistance
    2.52
     RESISTANCE
    2.44
    Activations Density 0.263%

    No Known Activations