© 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. 22-GEMMASCOPE-RES-131K
    7. 228
    Prev
    Next
    INDEX
    Explanations

    SQL `DECLARE` statements

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

    The neuron is detecting numeric literals (numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.48
     after
    -1.14
     with
    -1.07
     Both
    -1.03
    ͗
    -1.02
     because
    -1.01
     for
    -1.00
     of
    -0.99
     both
    -0.98
    DECREF
    -0.96
    POSITIVE LOGITS
     vern
    1.03
     pernic
    1.02
     Dorado
    1.01
     HOWARD
    1.00
    usually
    0.99
     shui
    0.96
     eus
    0.95
     PLAC
    0.94
     noten
    0.93
     zuk
    0.93
    Activations Density 0.008%

    No Known Activations