© 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. 34-GEMMASCOPE-RES-131K
    7. 117596
    Prev
    Next
    INDEX
    Explanations

    EJB remote beans

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

    The neuron fires strongly on occurrences of multi-letter uppercase technical acronyms (e.g. EJB, EAR) in Java EE contexts.

    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
    uhi
    -0.84
    Duo
    -0.75
    嬅
    -0.74
    Dile
    -0.73
     wanna
    -0.71
    dios
    -0.71
    Frida
    -0.71
    不得
    -0.71
    Ladder
    -0.69
    ਜ਼
    -0.69
    POSITIVE LOGITS
     ej
    1.52
    Remote
    1.44
    ejb
    1.41
     remote
    1.20
    remote
    1.20
    EJB
    1.19
    Bean
    1.11
     bean
    1.08
     Remote
    1.08
     Bean
    1.02
    Activations Density 0.045%

    No Known Activations