© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67105
    Prev
    Next
    INDEX
    Explanations

    repository and mapper patterns

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

    This neuron activates on Java data-access type names—specifically on class or interface identifiers ending in “Repository” or “Mapper.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ,’
    -1.69
     Tanpa
    -1.62
    矗
    -1.60
    ’,
    -1.55
    大幅
    -1.52
    特に
    -1.49
    ’).
    -1.48
     {
    -1.44
     with
    -1.39
     has
    -1.39
    POSITIVE LOGITS
    nuevos
    1.70
    mejores
    1.70
    buenos
    1.41
    nosotros
    1.40
     técn
    1.36
    huevos
    1.34
     khóa
    1.34
    diferentes
    1.33
    发生了
    1.32
    Воспита
    1.32
    Activations Density 0.001%

    No Known Activations