© 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. 100431
    Prev
    Next
    INDEX
    Explanations

    spring framework and java development

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

    Java code identifiers and programming-related tokens, particularly class names, method names, package names, and type declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by Java/Spring‐Boot code snippets, i.e. programming tokens like annotations, method names, identifiers, braces, 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_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
    😃
    -1.68
     Theologie
    -1.66
     theſe
    -1.61
    ☺
    -1.55
    👍🏻
    -1.54
    👍👍
    -1.54
    ❣
    -1.52
     блюдо
    -1.51
     Viol
    -1.48
    💪
    -1.46
    POSITIVE LOGITS
    我和
    1.51
    ַּ
    1.48
     of
    1.48
     only
    1.43
    ྱ
    1.41
     pouze
    1.38
    Spoljašnje
    1.38
    ְּ
    1.34
    ִּ
    1.33
     concerned
    1.31
    Activations Density 0.117%

    No Known Activations