© 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. 10-GEMMASCOPE-RES-131K
    7. 44344
    Prev
    Next
    INDEX
    Explanations

    education and educational status

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

    The main thing this neuron does is detect occurrences of the word “education” (and its variants like “educational” or “educated”).

    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
    硨
    -1.85
     humeur
    -1.59
     MARIE
    -1.56
    有一定
    -1.52
     ditt
    -1.45
    ⡯
    -1.44
    
    -1.43
    轵
    -1.43
     origine
    -1.42
     ingat
    -1.42
    POSITIVE LOGITS
     Ergänzung
    1.88
     Konkurrenz
    1.79
     häufig
    1.73
     a
    1.67
     jähr
    1.61
     ursprünglichen
    1.59
     ungewöhn
    1.58
     sogenannten
    1.58
     to
    1.56
     bedeut
    1.54
    Activations Density 0.015%

    No Known Activations