© 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. 91954
    Prev
    Next
    INDEX
    Explanations

    Spring framework beans

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

    The neuron is keyed to spotting Spring‐style Java annotations and related bean/configuration keywords (e.g. “@Bean,” “@Component,” “Configuration,” etc.).

    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
    ᵤ
    -0.77
    ugna
    -0.74
     dargestellt
    -0.72
     Worse
    -0.70
    breadcrumbs
    -0.69
     이동
    -0.68
    ubri
    -0.67
    ("")]
    -0.66
     Macedonian
    -0.66
    slice
    -0.66
    POSITIVE LOGITS
     bean
    2.22
     Bean
    1.84
    Bean
    1.79
     beans
    1.77
    bean
    1.67
    getBean
    1.32
    beans
    1.20
    BEAN
    1.13
     Beans
    1.10
    Beans
    1.09
    Activations Density 0.039%

    No Known Activations