© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104867
    Prev
    Next
    INDEX
    Explanations

    adding or creating code

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

    the word "add" or variations of it in programming contexts, particularly when adding handlers, collections, or other components to objects.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     –
    -2.16
    玏
    -2.13
    𖤣
    -1.99
    ">
    -1.88
     was
    -1.84
     nová
    -1.81
    "){
    -1.71
     unsere
    -1.70
    ꙮ
    -1.66
    </h2>
    -1.63
    POSITIVE LOGITS
    Following
    1.57
    會
    1.52
    because
    1.48
     Aggi
    1.45
     orizz
    1.44
     attiv
    1.42
    正义
    1.39
    女兒
    1.39
     スペース
    1.38
     unterkunft
    1.37
    Activations Density 0.001%

    No Known Activations