© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93124
    Prev
    Next
    INDEX
    Explanations

    association between different factors

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

    The neuron primarily picks out epidemiological study metadata—words and tokens associated with study design and titles (e.g. “Meta-analysis,” “Prospective Cohort Studies,” numbers, section headings).

    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
     whenever
    -0.83
     as
    -0.80
     immediately
    -0.77
    研究生
    -0.75
    三年
    -0.75
    苏州
    -0.74
     blatantly
    -0.74
    erg
    -0.73
     Whenever
    -0.72
     الفي
    -0.72
    POSITIVE LOGITS
    Associations
    0.91
     associations
    0.90
     olabilir
    0.90
     zelve
    0.90
    associations
    0.87
    開心
    0.86
    ālā
    0.85
    etui
    0.85
    tionnaire
    0.82
    errated
    0.81
    Activations Density 0.255%

    No Known Activations