© 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. 10123
    Prev
    Next
    INDEX
    Explanations

    SQL queries and statements

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

    abbreviations and keywords related to data manipulation language (DML) operations and query syntax in programming and database contexts.

    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
     on
    -1.55
     (
    -1.16
    '
    -1.15
    }));
    
    -1.09
     pela
    -1.05
     {
    -1.05
    }))
    
    -1.03
     which
    -1.02
     y
    -1.01
     которому
    -1.01
    POSITIVE LOGITS
     also
    1.65
     Synag
    1.50
     sekitarnya
    1.46
     gespeichert
    1.31
     edili
    1.30
    bague
    1.30
     essas
    1.28
     certainement
    1.28
     magnificent
    1.27
     także
    1.26
    Activations Density 0.077%

    No Known Activations