© 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. 66327
    Prev
    Next
    INDEX
    Explanations

    generic and biosimilar products

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

    pharmaceutical and medical terminology, particularly related to generic drugs and bioequivalence.

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

    This neuron detects mentions of monoclonal antibody drug names (i.e. terms ending in “–mab,” especially sequences like “iz umab”).

    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
    immortal
    -0.76
     Când
    -0.75
    casual
    -0.71
     Aidan
    -0.70
     interak
    -0.70
    Ձ
    -0.69
    Ֆ
    -0.69
     anomalies
    -0.69
    contaminated
    -0.68
    ığ
    -0.68
    POSITIVE LOGITS
     generic
    1.96
    generic
    1.71
    Generic
    1.53
     Generic
    1.50
     cheaper
    1.50
     gener
    1.50
     imitation
    1.41
    generics
    1.34
     equivalent
    1.33
     brand
    1.30
    Activations Density 0.042%

    No Known Activations