© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67214
    Prev
    Next
    INDEX
    Explanations

    MEDLINE searches

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

    The neuron identifies medical database names, particularly "MEDLINE", in scientific literature and academic paper abstracts.

    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
    鹛
    -2.13
    
    -1.88
    튿
    -1.84
     pérd
    -1.78
    zelfde
    -1.74
    隳
    -1.73
    縠
    -1.66
    镲
    -1.64
     cadeira
    -1.62
     sachsen
    -1.60
    POSITIVE LOGITS
     With
    1.84
     well
    1.69
    With
    1.63
     if
    1.53
     slight
    1.51
    Despite
    1.51
     parte
    1.50
    Another
    1.47
    Also
    1.45
     comforting
    1.45
    Activations Density 0.001%

    No Known Activations