© 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. 34-GEMMASCOPE-RES-131K
    7. 103728
    Prev
    Next
    INDEX
    Explanations

    programming language parsers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    閾
    -0.77
     радиа
    -0.75
    وای
    -0.74
    唠
    -0.74
    两年
    -0.72
     slums
    -0.70
    InvalidProtocol
    -0.69
    sianic
    -0.67
    赤ちゃん
    -0.67
     busy
    -0.67
    POSITIVE LOGITS
     AST
    1.95
    AST
    1.45
    Ast
    1.23
     grammar
    1.22
     visitor
    1.20
     parser
    1.20
     lex
    1.20
    visit
    1.18
     Ast
    1.17
     lexer
    1.11
    Activations Density 0.170%

    No Known Activations