© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    student programming and college activities

    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
     teachers
    -0.85
     TEACHERS
    -0.81
    teachers
    -0.79
    jects
    -0.77
     Teachers
    -0.75
     filings
    -0.74
     schoolmaster
    -0.73
     شکر
    -0.73
     científico
    -0.73
     disiplin
    -0.72
    POSITIVE LOGITS
     programming
    1.49
    Programming
    1.42
     Programming
    1.38
     student
    1.38
    Student
    1.34
    programming
    1.26
    学生
    1.22
     Student
    1.22
     programmer
    1.16
    student
    1.15
    Activations Density 0.028%

    No Known Activations