© 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. 11369
    Prev
    Next
    INDEX
    Explanations

    constructor calls for classes

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

    variable assignments and class instantiations in programming code, particularly using the `new` keyword or `=` operator with constructor calls.

    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
    0
    -1.48
    '
    -1.42
     after
    -1.42
     for
    -1.41
     will
    -1.36
     about
    -1.36
     related
    -1.30
     two
    -1.29
     "
    -1.24
     or
    -1.23
    POSITIVE LOGITS
     who
    1.67
    ⟬
    1.52
     there
    1.52
    甗
    1.50
     baisse
    1.42
     susc
    1.41
    Elő
    1.39
     persiste
    1.37
    罍
    1.37
     parrilla
    1.35
    Activations Density 0.059%

    No Known Activations