© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98065
    Prev
    Next
    INDEX
    Explanations

    biological roots and suffixes

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

    anatomical or medical tissue terms in scientific contexts.

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

    The neuron fires on recurring multi‐letter stems (e.g. “stri,” “di­alysis,” “haemo,” “medi­a­sti­na­l,” “hemato­po­ie­sis,” etc.), i.e. it detects the Greek‐ or Latin-derived root morphemes typical of biomedical/scientific terminology.

    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
    nél
    -1.03
    ebb
    -1.03
     spē
    -1.02
    冀
    -1.00
    ($__
    -1.00
    ornos
    -0.99
    忒
    -0.98
    cademic
    -0.97
    izaciones
    -0.95
    ıkları
    -0.94
    POSITIVE LOGITS
    特别是
    1.20
     comptes
    1.02
    Кто
    0.96
     Notwendigkeit
    0.92
     renov
    0.88
    щение
    0.88
    突入
    0.87
     ilust
    0.86
    веси
    0.86
    他にも
    0.85
    Activations Density 0.177%

    No Known Activations