© 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. 22-GEMMASCOPE-RES-131K
    7. 127824
    Prev
    Next
    INDEX
    Explanations

    The neuron is chiefly detecting common nouns (especially singular, countable things).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    inquiring or asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    责任编辑
    -1.30
     hilsen
    -1.16
     éter
    -1.14
    zija
    -1.11
    
    -1.09
    Répondre
    -1.08
     canel
    -1.08
    рани
    -1.06
    ίζει
    -1.05
    Gatt
    -1.05
    POSITIVE LOGITS
    I
    1.08
     etc
    1.05
    ↵↵
    0.96
    ycznie
    0.94
    harf
    0.94
     is
    0.93
    medy
    0.93
     and
    0.91
     į
    0.90
    insten
    0.89
    Activations Density 0.063%

    No Known Activations