© 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. 93839
    Prev
    Next
    INDEX
    Explanations

    education and schooling

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     tå
    -0.86
     conductas
    -0.86
    laire
    -0.85
    PLIED
    -0.82
     приложение
    -0.80
     ahorro
    -0.80
    HANDLING
    -0.77
    メント
    -0.77
     vänt
    -0.77
     ucap
    -0.76
    POSITIVE LOGITS
     education
    2.20
     schooling
    1.91
     Education
    1.87
    Education
    1.86
    education
    1.76
     attendance
    1.59
     educational
    1.56
     compulsory
    1.56
     enrolment
    1.47
     enrollment
    1.46
    Activations Density 0.024%

    No Known Activations