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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101157
    Prev
    Next
    INDEX
    Explanations

    public class

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

    the keyword "public" in Java code, specifically in class and method declarations.

    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
     regalar
    -2.03
     MÁS
    -1.94
     celta
    -1.66
     terão
    -1.66
     hué
    -1.62
     have
    -1.59
     existir
    -1.52
     kupić
    -1.49
     ciment
    -1.48
    依然
    -1.45
    POSITIVE LOGITS
    i
    2.03
    t
    2.03
     schreef
    1.62
    a
    1.61
    咝
    1.59
     kampen
    1.51
     vertelt
    1.50
    fashioned
    1.50
    b
    1.46
     Misc
    1.45
    Activations Density 0.008%

    No Known Activations