© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101277
    Prev
    Next
    INDEX
    Explanations

    population-based studies

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

    The neuron identifies phrases describing "population-based" studies or research methodologies in scientific literature.

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

    This neuron responds to hyphenated numeric ranges, as in sample-size or “population-based” study descriptors (e.g. “population 280-193 based”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    木坂
    -2.42
    涠
    -2.34
    The
    -2.16
    鹇
    -2.09
    getreten
    -2.09
    
    -2.05
    
    -2.05
    祧
    -2.03
    %")
    -2.02
    elesaikan
    -1.94
    POSITIVE LOGITS
    e
    2.19
    al
    2.17
    "
    2.11
    d
    2.03
     you
    1.93
    van
    1.92
    in
    1.90
     \
    1.89
    n
    1.86
    c
    1.86
    Activations Density 0.048%

    No Known Activations