© 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. 60590
    Prev
    Next
    INDEX
    Explanations

    obstructive pulmonary disease

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

    medical and scientific terms related to respiratory conditions, particularly "chronic obstructive pulmonary disease".

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

    The neuron flags specialized biomed-tech jargon—e.g. disease names (like “obstructive pulmonary”) and assay markers (like “Annexin V”).

    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
    补充
    -0.65
    Help
    -0.63
    wek
    -0.61
    Computation
    -0.60
     river
    -0.60
    allan
    -0.60
     Helena
    -0.59
    qing
    -0.59
    ЛЬ
    -0.59
    Executive
    -0.59
    POSITIVE LOGITS
     Petrus
    0.70
    trero
    0.69
     apostolic
    0.69
     antidepress
    0.67
    发出
    0.67
     apostle
    0.66
    Sue
    0.65
     seizures
    0.64
     Pave
    0.64
    omości
    0.64
    Activations Density 0.106%

    No Known Activations