© 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. 45439
    Prev
    Next
    INDEX
    Explanations

    neoplasia atypical cytology histological differentiation

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

    medical and histological terminology related to cell and tissue types in pathology reports.

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

    This neuron responds to specialized biomedical and pathology jargon—long, multi-syllable scientific terms (e.g., immunohistochemical, differentiation, neoplasia).

    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
     baada
    -0.88
    მ
    -0.81
     Parkway
    -0.81
     dynamical
    -0.79
     pathologies
    -0.78
     descubre
    -0.77
     короб
    -0.76
    सि
    -0.76
     CNRS
    -0.74
    chet
    -0.74
    POSITIVE LOGITS
     foc
    0.93
     digitale
    0.86
    sendTo
    0.86
    isenberg
    0.84
     INI
    0.82
     демон
    0.79
     ядер
    0.79
    sendMail
    0.78
     adm
    0.78
    (),"
    0.77
    Activations Density 0.340%

    No Known Activations