© 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. 81569
    Prev
    Next
    INDEX
    Explanations

    gender and age groups

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

    The neuron fires on words naming demographic groups—especially gender and age categories like “women,” “men,” “girls,” and “boys.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    しようと
    -0.84
    OnClickListener
    -0.83
     batería
    -0.81
    žių
    -0.81
    bein
    -0.80
    ssen
    -0.80
     personales
    -0.79
     contestants
    -0.79
    abo
    -0.79
    on
    -0.79
    POSITIVE LOGITS
     children
    2.38
     women
    2.38
     woman
    1.88
    women
    1.78
     men
    1.53
    children
    1.42
     Women
    1.40
     Children
    1.34
     kids
    1.33
     their
    1.32
    Activations Density 0.038%

    No Known Activations