© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    loved ones and their care

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

    This neuron detects language about caregiving—especially caring for aging, ill, or dependent loved ones.

    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
    チョコレート
    -0.84
     typer
    -0.82
    composer
    -0.81
    nians
    -0.79
     mle
    -0.79
    lui
    -0.79
     FEATURES
    -0.77
    黑的
    -0.76
    entown
    -0.76
    ABN
    -0.75
    POSITIVE LOGITS
     loved
    4.75
     Loved
    3.27
    loved
    3.20
    Loved
    3.13
     relatives
    2.88
     LOVED
    2.45
     relative
    2.23
     beloved
    2.00
    relative
    1.91
     liked
    1.84
    Activations Density 0.045%

    No Known Activations