© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79746
    Prev
    Next
    INDEX
    Explanations

    family members and relationships

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

    This neuron responds to words referring to family relationships (e.g., “family,” “mother,” “daughter”).

    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
     we
    -1.13
     if
    -1.03
     unsere
    -0.99
     in
    -0.97
     >
    -0.94
     Vita
    -0.90
     dekorasi
    -0.88
     there
    -0.88
     new
    -0.87
    ットン
    -0.84
    POSITIVE LOGITS
     italie
    1.07
    ИН
    1.06
    airro
    1.00
     Relatives
    1.00
    UrlResolution
    0.99
    銕
    0.97
    itarios
    0.96
     économies
    0.96
     vendeur
    0.95
     kommunik
    0.94
    Activations Density 0.035%

    No Known Activations