© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 305
    Prev
    Next
    INDEX
    Explanations

    class implements interface

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

    the keyword "implements" in code declarations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @jyhe0408

    The neuron specifically fires on occurrences of the “implements” keyword in code, marking classes that declare they implement an interface.

    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
    そして
    -1.85
    その
    -1.54
    それを
    -1.45
    ьере
    -1.39
    および
    -1.34
     those
    -1.27
     then
    -1.27
    与此同时
    -1.27
    もや
    -1.26
     by
    -1.17
    POSITIVE LOGITS
    '],
    
    1.49
    に挑戦
    1.44
    1.42
     trám
    1.39
     például
    1.38
    今度
    1.38
    */
    
    1.36
    が可能
    1.36
    </u>
    1.35
     블
    1.34
    Activations Density 0.003%

    No Known Activations