© 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. 69566
    Prev
    Next
    INDEX
    Explanations

    Database operations and schema definitions

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

    This neuron responds to uppercase SQL keywords and database‐related constants (e.g. CREATE, SELECT, SQLITE_* flags) in code snippets.

    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
     would
    -1.30
     will
    -1.30
    ühlen
    -1.21
     نداره
    -1.15
     såsom
    -1.12
     CYTHON
    -1.12
     montaje
    -1.09
    iligung
    -1.09
    widetext
    -1.08
     Wartawan
    -1.08
    POSITIVE LOGITS
     Vitamina
    1.34
     improvements
    1.28
     by
    1.28
    política
    1.27
    といふ
    1.23
    CARACTERIST
    1.16
    достатки
    1.16
    Beschrijving
    1.14
     inhabitants
    1.13
    archical
    1.11
    Activations Density 0.055%

    No Known Activations