© 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. 10-GEMMASCOPE-RES-131K
    4. 57632
    Prev
    Next
    INDEX
    Explanations

    delbrueckii, etiology, erythropoietin

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

    This neuron activates for scientific terms in Latin and technical terminology, particularly taxonomic names, medical terms, and chemical compounds.

    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
     When
    -2.81
     There
    -2.67
     touted
    -2.64
     achieves
    -2.56
     defeats
    -2.27
    ،
    -2.22
     有
    -2.22
     That
    -2.20
     betrek
    -2.19
     understand
    -2.17
    POSITIVE LOGITS
    '
    3.44
    li
    3.03
    {
    2.70
    ri
    2.52
    AL
    2.48
    ra
    2.31
     ナチュラル
    2.30
    and
    2.28
    '__
    2.28
    ere
    2.19
    Activations Density 0.056%

    No Known Activations