© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113247
    Prev
    Next
    INDEX
    Explanations

    bioavailability or repatriated

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

    The neuron spikes on long, multi‐morpheme words with Latin-style suffixes (e.g. “repatriated,” “bioavailability”) commonly found in formal or scientific writing.

    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
     It
    -2.84
     become
    -2.33
     has
    -2.25
     means
    -2.13
    s
    -2.09
    т
    -2.06
     opens
    -2.00
     will
    -1.98
     event
    -1.98
     involves
    -1.98
    POSITIVE LOGITS
    1
    2.66
    澌
    2.20
    ઐ
    2.06
     車場
    2.03
    СКИ
    2.02
    逦
    1.98
    ᜒ
    1.95
     намного
    1.95
    的大
    1.93
    .'/
    1.92
    Activations Density 0.002%

    No Known Activations