© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4323
    Prev
    Next
    INDEX
    Explanations

    home care and hospice

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

    The neuron fires on formal institutional or organizational terms, especially proper names and nouns in corporate or administrative contexts (e.g., hospital names, associations, “Services,” “Compliance,” etc.).

    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
    षण
    -0.73
    hôtel
    -0.69
    olata
    -0.69
    凧
    -0.68
     揚げ
    -0.68
    Hotel
    -0.67
     pewter
    -0.65
    cct
    -0.65
    っけ
    -0.65
    Prix
    -0.65
    POSITIVE LOGITS
     hospice
    2.48
     Hospice
    2.19
    Hosp
    1.47
     home
    1.19
     Home
    1.13
     hosp
    1.03
     agencies
    0.99
     Hosp
    0.96
     Visiting
    0.94
    hosp
    0.94
    Activations Density 0.024%

    No Known Activations