© 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. 12275
    Prev
    Next
    INDEX
    Explanations

    grouped, groupby, lazy, query

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

    code related to grouping, aggregation, or collection operations in programming 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
     bombe
    -1.48
     culte
    -1.37
     diamant
    -1.32
     chirurgie
    -1.30
    //{
    -1.26
     rigide
    -1.25
     itali
    -1.25
     hiver
    -1.25
     their
    -1.24
    RuleContext
    -1.24
    POSITIVE LOGITS
     to
    1.52
     different
    1.34
     have
    1.33
     четырех
    1.28
    蹶
    1.27
     flach
    1.26
     akce
    1.23
     four
    1.23
     мужчины
    1.21
     vinculado
    1.21
    Activations Density 0.064%

    No Known Activations