© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67589
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY

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

    The neuron activates on the SQL keyword “PRIMARY,” especially in “PRIMARY KEY” declarations.

    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
    </strong>
    -2.64
     Ähn
    -2.16
     ´
    -2.11
      
    -2.09
     _________
    -2.03
     _______
    -2.02
     magnific
    -1.98
    zmm
    -1.97
     terrific
    -1.95
     '
    -1.91
    POSITIVE LOGITS
    what
    2.19
    的问道
    2.17
     शुर
    2.17
    ஂ
    2.14
    
    2.13
    An
    2.11
    地说
    2.02
    蘗
    2.02
    𖡼
    2.00
     ataupun
    1.99
    Activations Density 0.011%

    No Known Activations