© 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. 22-GEMMASCOPE-RES-131K
    7. 28575
    Prev
    Next
    INDEX
    Explanations

    stay-at-home mom or dadhomemaker or housewife

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

    This neuron detects mentions of stay-at-home family roles or homemaking (e.g., stay-at-home mom/dad, homemaker).

    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
     to
    -1.07
    fficking
    -1.07
     they
    -1.01
    紀錄
    -0.95
     Wartawan
    -0.94
     even
    -0.93
    ájá
    -0.93
    Frankreich
    -0.92
     Each
    -0.90
    pédie
    -0.90
    POSITIVE LOGITS
     disponib
    1.26
     vocale
    1.23
    専
    1.16
     minimale
    1.09
    truction
    1.06
     débris
    1.06
    igné
    1.04
     inmig
    1.04
     télécommande
    1.02
    衩
    1.02
    Activations Density 0.010%

    No Known Activations