© 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. 2158
    Prev
    Next
    INDEX
    Explanations

    circulating biomarkers, cancer DNA

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

    scientific and medical terminology related to biological samples and laboratory techniques.

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

    The neuron responds to technical biomedical research terms (e.g. assay names, molecular markers, cell‐ or DNA‐related nouns).

    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
     Davidson
    -0.77
    呱
    -0.77
    antee
    -0.77
    setdefault
    -0.76
    Davidson
    -0.75
     Gottesdienst
    -0.75
     Grunds
    -0.72
    vorous
    -0.71
     Infection
    -0.69
     mouseClicked
    -0.68
    POSITIVE LOGITS
     circulating
    1.16
     ct
    1.11
     cf
    1.09
     CTC
    0.94
     cancer
    0.93
     CANCER
    0.90
     DNA
    0.90
    cancer
    0.82
    Circ
    0.82
     circulate
    0.81
    Activations Density 0.052%

    No Known Activations