© 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. 34800
    Prev
    Next
    INDEX
    Explanations

    Saudi Arabia politics

    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
    vaders
    -0.84
     Kuba
    -0.82
    бек
    -0.79
    udnio
    -0.79
    ępo
    -0.75
     Speeches
    -0.74
    akal
    -0.74
    ELO
    -0.72
     слабо
    -0.71
    }^{*}$
    -0.69
    POSITIVE LOGITS
     Khas
    1.38
     Jamal
    1.28
     Saudi
    1.22
    Saudi
    1.13
     جمال
    0.95
     murder
    0.90
     Washington
    0.88
     Turkey
    0.85
     journalist
    0.82
     consulate
    0.82
    Activations Density 0.010%

    No Known Activations