© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30808
    Prev
    Next
    INDEX
    Explanations

    sovereignty and integrity

    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
    大家好
    -0.79
    abilir
    -0.78
    ваете
    -0.75
    ЙТЕ
    -0.75
    ungere
    -0.75
    Fordítás
    -0.75
    wart
    -0.75
     menilai
    -0.74
     yet
    -0.74
    entrion
    -0.73
    POSITIVE LOGITS
     sovereignty
    2.53
     territorial
    2.23
     integrity
    2.05
     sovereign
    1.67
     Integrity
    1.55
    integrity
    1.54
    territ
    1.54
     терито
    1.43
     integridad
    1.33
     Territorial
    1.30
    Activations Density 0.014%

    No Known Activations