© 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. 32813
    Prev
    Next
    INDEX
    Explanations

    brand or type followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects the vertical bar characters (“|”) used in ASCII‐style tree or hierarchy diagrams.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    ૉ
    -1.23
     Often
    -1.20
     bereits
    -1.13
    Both
    -1.11
    Often
    -1.11
     Oft
    -1.05
     data
    -1.03
     this
    -1.01
     英文
    -1.00
     facilitates
    -1.00
    POSITIVE LOGITS
     trésor
    1.33
     lác
    1.18
    cketed
    1.16
     órganos
    1.12
     bâtiments
    1.11
     cúp
    1.10
    ఽ
    1.09
     meubles
    1.07
    ​​​
    1.06
    hooting
    1.05
    Activations Density 0.000%

    No Known Activations