© 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. 63028
    Prev
    Next
    INDEX
    Explanations

    socialist communist utopian ideals

    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
    meneu
    -0.86
    Legacy
    -0.79
    외
    -0.75
    וּ
    -0.75
    隆
    -0.74
    oussef
    -0.73
     McCulloch
    -0.73
     irrever
    -0.73
    Kam
    -0.73
    長
    -0.72
    POSITIVE LOGITS
     socialism
    1.80
     socialist
    1.75
     communism
    1.61
     Socialism
    1.51
     utopia
    1.49
     communal
    1.49
     communist
    1.39
     utopian
    1.35
     Communism
    1.32
     socialista
    1.32
    Activations Density 0.029%

    No Known Activations