© 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. 119020
    Prev
    Next
    INDEX
    Explanations

    database statements and cursors

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

    database cursor objects and related database connection statements in code.

    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
     quando
    -1.67
     cuando
    -1.61
     sartén
    -1.39
    ribue
    -1.38
     когда
    -1.37
    когда
    -1.35
    .‏
    -1.32
    眺望
    -1.30
     центр
    -1.28
     =-\
    -1.27
    POSITIVE LOGITS
     становятся
    1.90
     were
    1.54
     freilich
    1.42
     kérdés
    1.41
    .
    1.40
    Though
    1.39
    pecabe
    1.38
     yawn
    1.38
     видел
    1.38
    To
    1.38
    Activations Density 0.005%

    No Known Activations