© 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. 110899
    Prev
    Next
    INDEX
    Explanations

    database session types

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

    database-related keywords and syntax in code, particularly terms like "clause", "bool", "should", "must", "database", "session", "cache", "read", "write", and database system names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on programming-related identifiers—API keywords, DSL terms, class or method names, and other code-specific tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.58
    torre
    -1.27
     között
    -1.20
     seier
    -1.16
     он
    -1.16
     still
    -1.16
    慜
    -1.16
     in
    -1.16
    masque
    -1.12
     diha
    -1.10
    POSITIVE LOGITS
    ではでは
    1.35
     Andaman
    1.35
     последних
    1.35
     recto
    1.29
     there
    1.28
     JAXBElement
    1.27
    eo
    1.26
     ModelExpression
    1.26
    even
    1.25
     georgia
    1.25
    Activations Density 0.029%

    No Known Activations