© 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. 127660
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on document headings or titles enclosed in square brackets (i.e. bracketed section titles).

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

    multilingual content

    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
    Ghz
    -1.17
     tzu
    -1.14
     çantası
    -1.11
     bula
    -1.08
    الدراسه
    -1.08
     global
    -1.06
     United
    -1.05
     modelleri
    -1.02
     kazak
    -1.02
     bianca
    -1.01
    POSITIVE LOGITS
     nyingi
    1.27
    Translated
    1.23
    暧
    1.21
     nordrhein
    1.16
     Ähnliche
    1.13
     someone
    1.12
     شہر
    1.11
     órgano
    1.10
    謳
    1.08
     masculina
    1.06
    Activations Density 0.031%

    No Known Activations