© 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. 22-GEMMASCOPE-RES-131K
    7. 34128
    Prev
    Next
    INDEX
    Explanations

    @ Override

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

    This neuron detects annotation markers (the “@” symbol) in code, such as Java’s @Override.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     You
    -1.70
    🪆
    -1.49
     Erinner
    -1.46
    Mutagenicity
    -1.44
    逡
    -1.38
     "
    -1.33
    "¿
    -1.31
    🕗
    -1.30
     are
    -1.29
     Whether
    -1.29
    POSITIVE LOGITS
     />';
    1.18
    >
    1.12
     mortos
    1.12
     Toscana
    1.09
    コウ
    1.09
    スポンサーリンク
    1.05
     dimensi
    1.05
    ፝
    1.04
     Tó
    1.04
     promu
    1.02
    Activations Density 0.000%

    No Known Activations