© 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. 53788
    Prev
    Next
    INDEX
    Explanations

    students and academic years

    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
    kids
    -0.93
    Kids
    -0.85
    Teachers
    -0.84
    child
    -0.81
    แข
    -0.79
    jobs
    -0.76
    Parents
    -0.75
    boys
    -0.75
     TEACHERS
    -0.74
    Girls
    -0.73
    POSITIVE LOGITS
     students
    2.67
     student
    2.47
     студен
    1.87
     estudiantes
    1.85
    学生
    1.62
     estudiante
    1.62
     دانش
    1.61
     étudiants
    1.56
     студентов
    1.55
     mahasiswa
    1.52
    Activations Density 0.083%

    No Known Activations