© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118820
    Prev
    Next
    INDEX
    Explanations

    NOT NULL OR IS NULL

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

    The neuron fires on SQL negation constructs (e.g. “NOT”, “IS NOT”, “NOT NULL,” “NOT EXISTS”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     alfab
    -0.81
     marmor
    -0.81
    TRES
    -0.80
    Rhe
    -0.80
     Mondiale
    -0.78
    🙅
    -0.76
    篁
    -0.76
    Organisateur
    -0.76
    jupiter
    -0.75
    hef
    -0.75
    POSITIVE LOGITS
     null
    1.09
    null
    0.92
    istus
    0.85
     verdaderos
    0.82
     demuestra
    0.81
    Null
    0.75
     różnych
    0.72
    叶子
    0.72
    ustering
    0.71
     Insertion
    0.71
    Activations Density 0.005%

    No Known Activations