© 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. 33312
    Prev
    Next
    INDEX
    Explanations

    foreign words and technical terms

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

    The neuron detects programming identifiers—especially API/package names and class or enum constant tokens in code.

    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
    اكل
    -0.80
     Wiggins
    -0.73
     descu
    -0.72
    нача
    -0.71
     packing
    -0.71
     type
    -0.70
     visita
    -0.69
     chain
    -0.69
    微博
    -0.69
     ferry
    -0.68
    POSITIVE LOGITS
    wraps
    0.85
    obrázek
    0.81
    Читайте
    0.80
    disfraz
    0.80
    Ikus
    0.78
     seer
    0.78
    aceite
    0.78
     Geden
    0.77
    gunos
    0.77
    tênis
    0.76
    Activations Density 0.000%

    No Known Activations