© 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. 102994
    Prev
    Next
    INDEX
    Explanations

    philosophy of language and ethics

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

    The neuron flags scholarly philosophical content—names of philosophers, philosophical terms, and references to academic works.

    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
    dale
    -0.78
     נוסף
    -0.75
     premises
    -0.75
     inic
    -0.71
     proib
    -0.71
     numeri
    -0.70
     fortal
    -0.70
     decre
    -0.68
    medi
    -0.68
    enqueue
    -0.68
    POSITIVE LOGITS
     Wittgenstein
    1.20
    语言
    1.05
     language
    0.99
     Language
    0.93
    沁
    0.90
     زبان
    0.90
    Language
    0.88
     nyelv
    0.87
    genstein
    0.87
    language
    0.85
    Activations Density 0.023%

    No Known Activations