© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47873
    Prev
    Next
    INDEX
    Explanations

    KKK, Nazi, white supremacy, Tea Party

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags mentions of extremist or hate‐group references (e.g. KKK, Tea Party, neo-Nazis, white supremacists, lynch mobs, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    	
    -1.98
         
    -1.72
          
    -1.66
     ;
    -1.62
    /*
    -1.59
    Enjoy
    -1.59
     )
    -1.57
     $
    -1.55
    Also
    -1.55
    Do
    -1.55
    POSITIVE LOGITS
     fervor
    1.80
     lynch
    1.73
    MOVIE
    1.73
    鉝
    1.60
     alimentare
    1.60
     fundament
    1.58
     spati
    1.58
    zelfde
    1.52
     technic
    1.48
     comanda
    1.46
    Activations Density 0.014%

    No Known Activations