© 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. 34-GEMMASCOPE-RES-131K
    7. 32330
    Prev
    Next
    INDEX
    Explanations

    study design and participants

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

    The neuron identifies academic research terminology, particularly the word "study" and related research concepts like "analysis" and "participants."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     and
    -1.02
     این
    -0.98
     quí
    -0.91
    nhà
    -0.90
    uatu
    -0.88
    šiu
    -0.87
    lju
    -0.86
    Mã
    -0.85
    lja
    -0.85
    我先
    -0.84
    POSITIVE LOGITS
     objectives
    1.30
     period
    1.29
     participants
    1.18
     duration
    1.05
     objective
    1.01
     premises
    0.99
     outcome
    0.97
     sponsor
    0.96
    yah
    0.95
     design
    0.95
    Activations Density 0.118%

    No Known Activations