© 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. 81556
    Prev
    Next
    INDEX
    Explanations

    primary school

    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
     Teen
    -1.66
    Teen
    -1.61
     teenager
    -1.56
    高中
    -1.55
     teen
    -1.54
     teenagers
    -1.54
     teens
    -1.53
     Teens
    -1.35
    teen
    -1.32
    高校
    -1.30
    POSITIVE LOGITS
     primary
    1.36
     Primary
    1.28
     elementary
    1.17
    primary
    1.16
    Primary
    1.11
    小学校
    1.06
    児童
    1.05
    小学
    1.02
     children
    1.02
     PRIMARY
    1.01
    Activations Density 0.029%

    No Known Activations