© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92707
    Prev
    Next
    INDEX
    Explanations

    stay-at-home mom, hostess, homemaker

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

    This neuron activates on mentions of the subject’s mother (particularly statements about what the mother did or where she worked).

    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
     himself
    -1.44
     his
    -1.43
     boyhood
    -1.27
     jego
    -1.20
     condoms
    -1.18
     dads
    -1.16
     его
    -1.16
    娶
    -1.10
     father
    -1.10
     daddy
    -1.09
    POSITIVE LOGITS
     sewing
    1.40
     baking
    1.30
    sewing
    1.23
     herself
    1.21
     Sewing
    1.16
     knitting
    1.16
     hostess
    1.15
     nursing
    1.13
     needle
    1.12
     croche
    1.10
    Activations Density 0.023%

    No Known Activations