© 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. 102020
    Prev
    Next
    INDEX
    Explanations

    java class reflection

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

    the keyword "class" in programming code, particularly in class declarations and type definitions.

    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
     ſy
    -1.52
     publicó
    -1.45
     utilisent
    -1.40
    跸
    -1.38
     vijf
    -1.38
     mimicking
    -1.38
    䜣
    -1.34
     predominantly
    -1.34
     própri
    -1.34
     pensent
    -1.33
    POSITIVE LOGITS
     these
    1.62
    Like
    1.53
     Like
    1.47
     this
    1.42
     reduce
    1.40
     During
    1.39
    這些
    1.38
     like
    1.37
    Since
    1.37
     Despite
    1.36
    Activations Density 0.011%

    No Known Activations