© 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. 103976
    Prev
    Next
    INDEX
    Explanations

    code declarations: Int, String

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

    the data type "Int" in programming code.

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

    This neuron responds to occurrences of type identifiers (especially primitive types like Int, Bool, String) in Swift code.

    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
    ors
    -2.33
    鶲
    -2.03
     Inſ
    -1.97
    厛
    -1.95
     hunde
    -1.95
    峩
    -1.95
    桖
    -1.95
    BindingResult
    -1.88
    
    -1.86
     bizi
    -1.85
    POSITIVE LOGITS
     and
    1.95
     would
    1.83
     if
    1.65
     contains
    1.59
     that
    1.56
    <bos>
    1.54
    但在
    1.46
    ?
    1.45
     nunmehr
    1.45
     что
    1.45
    Activations Density 0.005%

    No Known Activations