© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38493
    Prev
    Next
    INDEX
    Explanations

    programming, languages, places, and code snippets

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

    This neuron detects programming‐related terms and code tokens (e.g. function definitions, SQL adapters, code keywords).

    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
    Usuarios
    -0.90
     lavorare
    -0.82
    indis
    -0.81
     indis
    -0.80
     Crockett
    -0.75
    zęd
    -0.74
    ším
    -0.74
    parole
    -0.73
    テキ
    -0.73
     inclination
    -0.72
    POSITIVE LOGITS
     Malayalam
    1.07
    kony
    1.06
     kony
    1.02
    Skin
    0.92
     Bengaluru
    0.91
     Tamil
    0.88
     Kannada
    0.86
     Bangalore
    0.84
     Palm
    0.84
    KA
    0.81
    Activations Density 0.003%

    No Known Activations