© 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. 127925
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to content-bearing words (i.e. domain‐specific nouns, verbs, adjectives, and other non–stopwords) rather than function words.

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

    proper names and titles

    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
     Möglich
    -0.96
     artikke
    -0.90
     Käufer
    -0.88
    localVar
    -0.88
     Organización
    -0.83
     Opiniones
    -0.83
     joyería
    -0.82
     Eocene
    -0.82
     Vorgang
    -0.81
     which
    -0.81
    POSITIVE LOGITS
    SFER
    0.87
    顶级
    0.86
    Ferry
    0.85
     Schon
    0.84
    dei
    0.83
    vies
    0.82
     Shukla
    0.81
    )",
    0.81
     rambling
    0.81
    ⭐
    0.80
    Activations Density 0.077%

    No Known Activations