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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64771
    Prev
    Next
    INDEX
    Explanations

    resource files

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

    The neuron activates on occurrences of the word “resource” or “resources” (as in import/include paths or file references) in code or markup.

    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
     there
    -0.79
     кіль
    -0.70
     建
    -0.69
    过去了
    -0.69
    笔记
    -0.66
    Garantie
    -0.65
    することを
    -0.65
    水彩
    -0.65
    aç
    -0.64
     Making
    -0.63
    POSITIVE LOGITS
     اللغة
    0.97
     tractor
    0.90
     égard
    0.89
     ResourceManager
    0.88
    owanej
    0.84
     multe
    0.83
     THOMAS
    0.79
     junior
    0.79
     JOSEPH
    0.78
    ultur
    0.78
    Activations Density 0.000%

    No Known Activations