© 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. 127816
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to the “{” token that opens a code block (e.g. the curly brace beginning a class or function body).

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

    code structure and technical terms

    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
    分かります
    -1.14
    struzione
    -1.09
     توضی
    -1.05
    Elaboración
    -1.02
     大きい
    -0.99
    ทั้งหมด
    -0.98
    łąd
    -0.97
    鼍
    -0.97
     cooperativa
    -0.97
     konsult
    -0.96
    POSITIVE LOGITS
     with
    1.05
     лишь
    1.04
     in
    1.00
     and
    0.99
    
    0.98
    一応
    0.96
    aktery
    0.96
    をご紹介
    0.95
    </b>
    0.94
     européennes
    0.93
    Activations Density 0.000%

    No Known Activations