© 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. 11377
    Prev
    Next
    INDEX
    Explanations

    suffix -ny, -ism, -ery, -valry OR prefix "ant-", "miso-", "pedo-"

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

    The neuron consistently lights up on words that denote ideological biases or hatreds (–isms and –phobias), such as misogyny/misogynistic, transphobic, nihilism, misanthropy, 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
    읭
    -1.97
     importanza
    -1.96
     envisioned
    -1.88
     нужен
    -1.88
    
    -1.83
     revelado
    -1.81
    PUESTA
    -1.80
    睥
    -1.80
    怍
    -1.78
    沺
    -1.77
    POSITIVE LOGITS
    {
    2.73
    ↵
    2.50
    "
    2.02
    \
    1.83
    ?
    1.78
    *
    1.69
    ↵↵
    1.67
     ―
    1.60
    </b>
    1.58
     هم
    1.58
    Activations Density 0.003%

    No Known Activations