© 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. 127761
    Prev
    Next
    INDEX
    Explanations

    This neuron detects names of software projects or products (proper nouns for tools/frameworks) often split across tokens.

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

    software names and related words

    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
    dö
    -1.73
     this
    -1.38
    źródło
    -1.34
    ösen
    -1.28
     these
    -1.27
    十七
    -1.26
    Karakter
    -1.26
     their
    -1.23
    Ár
    -1.23
    ！！！
    -1.20
    POSITIVE LOGITS
     your
    1.46
     you
    1.35
    though
    1.30
     erzeugen
    1.29
    SYSTEM
    1.29
    Ārējās
    1.27
     ecosystem
    1.22
    sp
    1.22
     gbc
    1.21
     vilja
    1.20
    Activations Density 0.095%

    No Known Activations