© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108225
    Prev
    Next
    INDEX
    Explanations

    international systems and relations

    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
     nationwide
    -0.80
    SRV
    -0.78
    Dès
    -0.73
    ೪
    -0.72
    ७
    -0.72
     Pey
    -0.71
     воин
    -0.71
    Government
    -0.71
    ೬
    -0.70
    vt
    -0.70
    POSITIVE LOGITS
     international
    1.58
     multilateral
    1.41
     rules
    1.32
     order
    1.25
    international
    1.23
     multip
    1.21
    rules
    1.20
     global
    1.17
    Rules
    1.09
     INTERNATIONAL
    1.08
    Activations Density 0.022%

    No Known Activations