© 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. 34-GEMMASCOPE-RES-131K
    7. 77200
    Prev
    Next
    INDEX
    Explanations

    providing care or looking after

    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
    бовать
    -0.77
     профилакти
    -0.73
     ज्ञात
    -0.72
    PC
    -0.69
    ahrt
    -0.66
     Beard
    -0.64
     tặng
    -0.64
    OkHttpClient
    -0.64
     отдых
    -0.63
    urnum
    -0.63
    POSITIVE LOGITS
     care
    4.28
     caring
    3.91
     cared
    3.23
    Caring
    3.05
    caring
    2.97
     cuidar
    2.94
    care
    2.92
     caretaker
    2.80
     cares
    2.78
     Caring
    2.78
    Activations Density 0.067%

    No Known Activations