© 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. 34-GEMMASCOPE-RES-131K
    7. 83155
    Prev
    Next
    INDEX
    Explanations

    database types and column names

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

    The neuron detects SQL data‐type specifications—i.e. tokens where a column or expression is declared or cast with types like VARCHAR, NVARCHAR, BIGINT, FLOAT, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    tiera
    -0.84
     exceptions
    -0.77
    vā
    -0.77
     clor
    -0.75
    ERIA
    -0.74
    mpada
    -0.74
    setBounds
    -0.72
    儺
    -0.71
    tidos
    -0.71
    karni
    -0.71
    POSITIVE LOGITS
    nvarchar
    0.84
     giám
    0.77
     dbo
    0.76
    Adverten
    0.76
     ceea
    0.75
    spicy
    0.75
    Chromosome
    0.75
    Sev
    0.74
    ából
    0.74
    Memento
    0.74
    Activations Density 0.005%

    No Known Activations