© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3433
    Prev
    Next
    INDEX
    Explanations

    introduction to courses

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

    The neuron fires on tokens naming academic subjects, courses, or department titles (e.g. “Department of Equine Science,” “CS,” “C++,” “Business,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    SPEAKER
    -0.83
    既存
    -0.70
    PECT
    -0.69
    sság
    -0.68
     encant
    -0.68
     blogger
    -0.68
    ALIA
    -0.68
     GUIDELINES
    -0.68
    lccc
    -0.67
    arthritis
    -0.67
    POSITIVE LOGITS
     fundamentals
    1.17
     Fundamentals
    1.12
     thermodynamics
    1.11
     Constitutional
    1.06
     Introduction
    1.05
     Thermodynamics
    1.04
     Intro
    1.02
    Intro
    1.01
     Basics
    0.98
     Foundations
    0.98
    Activations Density 0.030%

    No Known Activations