© 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. 22-GEMMASCOPE-RES-131K
    7. 59
    Prev
    Next
    INDEX
    Explanations

    schools, education, and curriculum

    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_22/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
    konstruktion
    -1.26
    ଆ
    -1.24
    glä
    -1.17
     preva
    -1.16
    颊
    -1.14
     femmes
    -1.13
    Удачи
    -1.12
     juft
    -1.11
     prius
    -1.11
    inafter
    -1.10
    POSITIVE LOGITS
     curriculum
    1.60
     education
    1.48
     teaching
    1.47
     those
    1.38
     school
    1.36
     Werken
    1.34
     стекла
    1.34
     students
    1.33
     learning
    1.31
     modules
    1.30
    Activations Density 0.054%

    No Known Activations