© 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. 22-GEMMASCOPE-RES-131K
    7. 15827
    Prev
    Next
    INDEX
    Explanations

    SQL UPDATE statements

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

    The neuron fires on code fragments where a boolean field or flag is being assigned a true/false value.

    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
     for
    -1.21
    цыя
    -0.91
    可是
    -0.90
     could
    -0.89
     nosso
    -0.85
     with
    -0.84
     funkci
    -0.83
     Sparkle
    -0.82
    いただける
    -0.81
     might
    -0.80
    POSITIVE LOGITS
    suited
    1.01
    endregion
    1.00
     ABBREVIATIONS
    0.97
    ņi
    0.97
     increased
    0.94
     now
    0.94
     descendre
    0.94
    paraiso
    0.94
    备注
    0.93
    increased
    0.93
    Activations Density 0.005%

    No Known Activations