© 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. 127702
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on key content words (technical nouns and verbs) in explanatory or descriptive passages, ignoring domain labels and function words.

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

    processing and containment

    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
     even
    -1.33
     just
    -1.27
     staunch
    -1.22
    了一些
    -1.20
     with
    -1.18
     notorious
    -1.10
     if
    -1.05
     an
    -1.03
     schon
    -1.03
     and
    -1.00
    POSITIVE LOGITS
     distinguer
    1.20
     bensin
    1.19
     poë
    1.16
     nhat
    1.16
    etna
    1.10
     anúncios
    1.08
     tracción
    1.08
    最终
    1.08
     interesses
    1.08
    imee
    1.06
    Activations Density 0.129%

    No Known Activations