© 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. 10-GEMMASCOPE-RES-131K
    7. 86704
    Prev
    Next
    INDEX
    Explanations

    prejudice and preposterous

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

    The main thing this neuron does is detect the word “prejudice” (and closely related bias‐ or discrimination‐themed terms).

    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
    ne
    -2.56
    ࿚
    -2.55
    ৢ
    -2.52
     включая
    -2.50
    僂
    -2.47
    ]
    -2.45
     souligné
    -2.44
    我才
    -2.36
    ၞ
    -2.34
    家主
    -2.33
    POSITIVE LOGITS
    '
    3.42
     駅前
    2.83
     也
    2.61
     белые
    2.48
     oock
    2.47
     laget
    2.38
     飯店
    2.33
     daer
    2.33
    2
    2.33
     纹身
    2.31
    Activations Density 0.002%

    No Known Activations