© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74238
    Prev
    Next
    INDEX
    Explanations

    care about or for

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

    This neuron detects expressions of caring or concern, especially the phrase “care about.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Ꮏ
    -1.88
    哢
    -1.86
    teilungen
    -1.86
     astuces
    -1.68
    誑
    -1.67
     OGSÅ
    -1.67
    枻
    -1.67
     behö
    -1.66
    噥
    -1.66
    şap
    -1.66
    POSITIVE LOGITS
    ↵↵
    2.19
    </strong>
    1.95
    {
    1.80
    </h3>
    1.80
     it
    1.66
    but
    1.64
    /
    1.63
     taką
    1.54
    0
    1.49
    ↵↵↵
    1.48
    Activations Density 0.018%

    No Known Activations