© 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. 22-GEMMASCOPE-RES-131K
    7. 14279
    Prev
    Next
    INDEX
    Explanations

    care followed by giving or for

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

    The neuron strongly activates on the word “care” (and its variants like “caregiving” or “caregiver”), i.e. it detects mentions of care-related terms.

    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
    '
    -3.11
    籏
    -2.36
    皷
    -2.16
     アレンジ
    -2.13
    ৄ
    -2.11
    表紙
    -2.05
    ortiment
    -2.05
    ستخدم
    -2.03
    秫
    -2.03
    ندا
    -2.02
    POSITIVE LOGITS
    o
    3.00
    as
    2.63
    ۔
    2.38
    蔔
    2.36
    out
    2.20
    ebenarnya
    2.19
     daring
    2.16
    or
    2.11
     інші
    2.11
    that
    2.09
    Activations Density 0.033%

    No Known Activations