© 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. 98737
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    The neuron fires on technical biomedical entity names—particularly disease and syndrome names (and related medical terms).

    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
     only
    -1.43
     this
    -1.42
     continues
    -1.41
    [
    -1.34
     vẫn
    -1.29
     только
    -1.26
     to
    -1.22
    ercizio
    -1.17
    >
    -1.15
    Ţ
    -1.12
    POSITIVE LOGITS
     like
    1.34
     such
    1.30
    such
    1.29
    說是
    1.27
    頃は
    1.24
     renforcer
    1.21
     stratég
    1.20
     membagikan
    1.18
     összefoglaló
    1.18
    わない
    1.18
    Activations Density 0.105%

    No Known Activations