© 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. 119261
    Prev
    Next
    INDEX
    Explanations

    societal topics and issues

    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
     Wikimédia
    -0.94
     blancs
    -0.93
     africains
    -0.92
    éri
    -0.90
    ytä
    -0.88
    \{\\
    -0.87
     Архиви
    -0.87
     supérieurs
    -0.86
    OnClickListener
    -0.85
     彩色
    -0.85
    POSITIVE LOGITS
     health
    1.70
     topics
    1.65
     issues
    1.59
     economic
    1.53
     sexual
    1.52
    topics
    1.51
     food
    1.46
     climate
    1.40
     immigration
    1.38
     religion
    1.38
    Activations Density 0.130%

    No Known Activations