© 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. 107084
    Prev
    Next
    INDEX
    Explanations

    spouses and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    вочка
    -0.81
     boyhood
    -0.79
    噻
    -0.74
     Imported
    -0.72
    ongan
    -0.71
    utzen
    -0.70
     export
    -0.70
    KAY
    -0.69
    สาว
    -0.69
    łys
    -0.69
    POSITIVE LOGITS
     spouse
    5.69
     spouses
    4.94
     Spouse
    4.03
    spouse
    4.00
    Spouse
    3.78
     spousal
    3.08
     супру
    2.77
     wife
    2.59
     husband
    2.56
     همسر
    2.38
    Activations Density 0.056%

    No Known Activations