© 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. 22-GEMMASCOPE-RES-131K
    7. 68055
    Prev
    Next
    INDEX
    Explanations

    medical conditions and risks

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

    This neuron activates for medical and scientific terms in academic papers about physiology, diseases, and treatments.

    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_22/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
     掃除
    -1.62
    brtc
    -1.34
     maladies
    -1.34
     celebró
    -1.32
     automatisch
    -1.31
     eſt
    -1.30
     стихотво
    -1.30
     ſen
    -1.28
     ſon
    -1.27
     uſ
    -1.27
    POSITIVE LOGITS
     caution
    1.58
     or
    1.54
     clás
    1.53
     may
    1.51
     heightened
    1.38
     increased
    1.36
     decreases
    1.34
     decreased
    1.32
     including
    1.30
     specifically
    1.29
    Activations Density 0.659%

    No Known Activations