© 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. 10-GEMMASCOPE-RES-131K
    4. 11212
    Prev
    Next
    INDEX
    Explanations

    get/set method calls

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

    method or function calls that retrieve or access data, particularly getter functions in code.

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

    The neuron triggers on code tokens that are method names—especially those beginning with “Get” (and to a lesser extent “Set”)—i.e. getter/setter function calls.

    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
     แต่
    -1.91
     некоторые
    -1.66
    烀
    -1.63
     But
    -1.62
     sommige
    -1.56
     “
    -1.55
    タイプの
    -1.53
     zís
    -1.49
     används
    -1.45
     tačiau
    -1.45
    POSITIVE LOGITS
     there
    2.03
    谘
    1.64
     that
    1.59
    𐑂
    1.56
     until
    1.54
     eight
    1.52
    Since
    1.52
    ,
    1.51
     any
    1.49
     providing
    1.48
    Activations Density 0.003%

    No Known Activations