© 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. 10-GEMMASCOPE-RES-131K
    7. 104562
    Prev
    Next
    INDEX
    Explanations

    amyloid plaque and myeloid leukemia

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

    medical terms related to amyloid proteins and diseases.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is strongly activated by occurrences of “amyloid” (and closely related disease terms ending in “-idosis”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    frac
    -3.05
    刧
    -2.97
     thrilling
    -2.88
    m
    -2.86
    棪
    -2.70
    卨
    -2.64
    「
    -2.63
    程度上
    -2.55
     кожу
    -2.39
     \%)$
    -2.31
    POSITIVE LOGITS
    咵
    2.81
    3
    2.75
    鱨
    2.59
    0
    2.48
    7
    2.42
    会有
    2.41
    2
    2.34
     какие
    2.31
    
    2.30
    的时候
    2.27
    Activations Density 0.010%

    No Known Activations