© 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. 103961
    Prev
    Next
    INDEX
    Explanations

    `null` or `not null` constraints

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

    keywords indicating non-null database constraints or boolean values in code, particularly "NOT NULL" in SQL and "True/False" or "null=" in Python/Django code.

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

    The neuron fires on nullability and “blank” constraints in model or table field definitions (e.g. null=True/False, blank=True/False, NOT NULL).

    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
     a
    -2.39
     one
    -1.55
     three
    -1.52
     while
    -1.48
    //
    -1.40
    :
    -1.39
     bawat
    -1.38
     would
    -1.37
     habang
    -1.35
    while
    -1.34
    POSITIVE LOGITS
    âneo
    1.50
     aislados
    1.50
    Artículos
    1.41
    
    1.41
    Día
    1.41
    Misión
    1.39
    käse
    1.38
     innych
    1.38
     festen
    1.37
     vollständ
    1.36
    Activations Density 0.002%

    No Known Activations