© 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. 55747
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and fields

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

    The neuron flags technical, scientific, or methodological jargon—especially names of disciplines and related domain‐specific terms.

    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
     maladie
    -0.91
    healthcare
    -0.88
     algún
    -0.88
     doença
    -0.81
     beleza
    -0.79
     cobertura
    -0.79
    Beauty
    -0.79
     FINANCIAL
    -0.79
     stitching
    -0.78
    rusted
    -0.78
    POSITIVE LOGITS
     psychology
    2.19
     sociology
    2.00
     biology
    1.89
     anthropology
    1.83
     geology
    1.83
     physics
    1.67
     economics
    1.66
     hydrology
    1.63
     linguistics
    1.60
     biochemistry
    1.60
    Activations Density 0.232%

    No Known Activations