© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90891
    Prev
    Next
    INDEX
    Explanations

    philosophy of science

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

    This neuron fires on content words in academic‐style titles or headings—especially capitalized terms in paper/book names and section headings.

    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
    bp
    -0.84
     Ignatius
    -0.79
    PARAMS
    -0.79
     Scholars
    -0.78
     αρχ
    -0.78
     Baba
    -0.76
     baba
    -0.74
     Thiru
    -0.73
    gradation
    -0.73
    impl
    -0.72
    POSITIVE LOGITS
     scientific
    0.92
     instrumental
    0.87
     epistem
    0.87
     philosophy
    0.82
    Scientific
    0.79
    哲学
    0.79
    phils
    0.79
     demarcation
    0.76
     science
    0.75
     nhẹ
    0.75
    Activations Density 0.022%

    No Known Activations