© 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. 22-GEMMASCOPE-RES-131K
    7. 130443
    Prev
    Next
    INDEX
    Explanations

    This neuron identifies Java Lombok annotation and related import keywords (e.g. AccessLevel, NoArgsConstructor, RequiredArgsConstructor).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Java class constructors and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -1.34
     prevé
    -1.28
     in
    -1.28
    Več
    -1.27
     also
    -1.21
     nena
    -1.20
    unjungi
    -1.20
     metais
    -1.19
     Američ
    -1.19
    実感
    -1.16
    POSITIVE LOGITS
    ままで
    1.41
    Don
    1.17
     rassemb
    1.13
    各有
    1.13
    Be
    1.13
    செ
    1.12
    osten
    1.11
    preise
    1.09
     попро
    1.09
    delta
    1.07
    Activations Density 0.000%

    No Known Activations