© 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. 22-GEMMASCOPE-RES-131K
    4. 92943
    Prev
    Next
    INDEX
    Explanations

    ethnic groups and origin

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

    The neuron responds to mentions of “ethnic” (and related terms like “ethnic groups” or “ethnic minorities”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    In
    -1.99
    This
    -1.97
    </h3>
    -1.91
    ));
    -1.88
    轳
    -1.84
     antworte
    -1.80
    You
    -1.79
     They
    -1.76
     =
    -1.71
         
    -1.69
    POSITIVE LOGITS
     diki
    2.61
     kapak
    2.61
     kemer
    2.48
     dekoratif
    2.36
     sœurs
    2.28
     kalori
    2.28
     vokal
    2.22
    OOTD
    2.22
     balon
    2.19
     göm
    2.14
    Activations Density 0.012%

    No Known Activations