© 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. 47961
    Prev
    Next
    INDEX
    Explanations

    international organizations and classifications

    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
     biodiversity
    -0.88
     Kids
    -0.82
    なさい
    -0.81
     firewall
    -0.80
     biomarkers
    -0.80
     genomics
    -0.78
     stakeholder
    -0.77
     partnering
    -0.77
    enangan
    -0.75
     &[
    -0.75
    POSITIVE LOGITS
     Unesco
    1.11
     UNESCO
    0.93
    .《
    0.88
    UNESCO
    0.85
     juri
    0.79
    Diem
    0.78
     organizations
    0.78
    Pile
    0.78
    这类
    0.78
    Consultation
    0.77
    Activations Density 0.033%

    No Known Activations