© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127537
    Prev
    Next
    INDEX
    Explanations

    relapsing remitting multiple sclerosis

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

    The neuron detects the word "remission" or variations like "remitted" in medical contexts.

    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
    衚
    -2.89
    蹌
    -2.67
    actéristi
    -2.66
    킁
    -2.48
    ⸫
    -2.48
     behaupten
    -2.41
    ⃠
    -2.36
     bestens
    -2.33
     unterschiedlich
    -2.33
     hervorragend
    -2.31
    POSITIVE LOGITS
    ↵
    2.83
     That
    2.78
    ),
    2.38
     While
    2.36
     Those
    2.25
     is
    2.22
     When
    2.22
     inmediatamente
    2.17
     únicamente
    2.16
     Using
    2.14
    Activations Density 0.002%

    No Known Activations