© 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. 116912
    Prev
    Next
    INDEX
    Explanations

    student or school related contexts

    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
    WOMEN
    -0.79
     населення
    -0.77
     Lympho
    -0.77
    kunt
    -0.76
    Sev
    -0.73
     Sev
    -0.71
    mobil
    -0.71
    ORAGE
    -0.70
     kvinder
    -0.70
     Applicant
    -0.69
    POSITIVE LOGITS
     student
    1.50
     students
    1.41
     district
    1.30
    student
    1.19
    Students
    1.13
    students
    1.10
     school
    1.09
     STUDENT
    1.09
     instructional
    1.08
     öğren
    1.08
    Activations Density 0.009%

    No Known Activations