© 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. 22695
    Prev
    Next
    INDEX
    Explanations

    names of things

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

    The neuron fires on occurrences of the substring “bili” (as in bilirubin measurements) in the text.

    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
    葯
    -2.17
     proactively
    -2.05
    I
    -1.99
    榇
    -1.98
     godk
    -1.96
     ‘
    -1.95
    L
    -1.91
    سكري
    -1.88
     navide
    -1.88
     tirelessly
    -1.86
    POSITIVE LOGITS
    .
    2.23
    sandalia
    1.85
     It
    1.81
    ⽤
    1.75
    ↵↵
    1.75
     erforder
    1.74
    之为
    1.72
    这般
    1.71
    🟧
    1.67
    日で
    1.66
    Activations Density 0.023%

    No Known Activations