© 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. 34-GEMMASCOPE-RES-131K
    7. 47309
    Prev
    Next
    INDEX
    Explanations

    Go code syntax and technical terms

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

    The neuron responds strongly to code punctuation marks (e.g. commas, parentheses, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    úly
    -0.77
    覧
    -0.76
    АК
    -0.76
     truly
    -0.74
    ЕВ
    -0.73
     туры
    -0.72
    海苔
    -0.71
    átiles
    -0.70
     запись
    -0.68
    શ
    -0.68
    POSITIVE LOGITS
    omitempty
    1.13
    alny
    0.91
     discípulos
    0.79
    
    0.79
     Justiz
    0.77
     específicas
    0.76
     SPECIFIC
    0.75
    жли
    0.75
     attraction
    0.75
    دیگر
    0.74
    Activations Density 0.002%

    No Known Activations