© 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. 38649
    Prev
    Next
    INDEX
    Explanations

    qualitative and quantitative research methods

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

    The neuron is selectively activated by numeric or quantitative tokens—i.e. numbers and numerical measurements or statistics in the text.

    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
     researchers
    -0.88
    大学の
    -0.86
     Researchers
    -0.83
     鼠
    -0.82
    ?*
    -0.80
    !*
    -0.79
    ğum
    -0.78
     Wissenschaftler
    -0.74
    ⁉
    -0.74
     tut
    -0.73
    POSITIVE LOGITS
     quantitative
    2.48
     qualitative
    2.34
    quantitative
    1.93
     mixed
    1.85
    Quantitative
    1.83
     Qualitative
    1.74
     interviews
    1.70
     Quantitative
    1.69
     quantitatively
    1.68
    Qualitative
    1.68
    Activations Density 0.147%

    No Known Activations