© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    health and social support

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

    medical and scientific terms or conditions in academic contexts.

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

    The neuron strongly fires on the main content‐bearing nouns in scientific or clinical abstracts—especially specialized, domain-specific terms (e.g. dementia, BPSD, care home, informal caregivers, hemorrhoids, magnetic disk).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     that
    -2.05
     this
    -1.44
     both
    -1.27
    いえば
    -1.27
    \
    -1.26
     by
    -1.24
    帰る
    -1.20
     albeit
    -1.15
    \#:
    -1.14
     the
    -1.13
    POSITIVE LOGITS
     тях
    1.51
     когато
    1.45
     вони
    1.45
    他
    1.42
    stawa
    1.41
    他们
    1.37
    תודה
    1.37
    шите
    1.35
     ihnen
    1.34
    ρός
    1.34
    Activations Density 0.084%

    No Known Activations