© 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. 10-GEMMASCOPE-RES-131K
    7. 22623
    Prev
    Next
    INDEX
    Explanations

    programming languages

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

    The neuron fires on mentions of programming language names (e.g., Python, JavaScript, Java, C++).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ໊
    -1.69
     první
    -1.52
     it
    -1.47
    鸩
    -1.43
     Они
    -1.41
    ⇡
    -1.40
    ᐕ
    -1.40
    beria
    -1.40
    ȭ
    -1.38
    ,’
    -1.35
    POSITIVE LOGITS
     &
    1.47
     especially
    1.43
    繋がり
    1.21
     کنید
    1.21
    especially
    1.20
    сора
    1.19
     even
    1.13
    D
    1.09
    erapeutics
    1.08
     bune
    1.08
    Activations Density 0.547%

    No Known Activations