© 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. 10-GEMMASCOPE-RES-131K
    7. 102143
    Prev
    Next
    INDEX
    Explanations

    maintaining homeostasis

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

    This neuron identifies the term "homeostasis" in biological and medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Our
    -2.39
     The
    -2.28
     That
    -2.23
    en
    -2.20
     Then
    -2.17
     октя
    -2.14
     encabez
    -2.06
     angezeigt
    -2.03
     cabelos
    -1.99
    筇
    -1.95
    POSITIVE LOGITS
    before
    2.17
    Ⲉ
    2.14
    whether
    2.08
    ☫
    2.06
    熜
    2.03
    甍
    2.00
    }_{
    1.98
    even
    1.98
     entr
    1.97
    ୌ
    1.95
    Activations Density 0.009%

    No Known Activations