© 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. 10-GEMMASCOPE-RES-131K
    7. 110919
    Prev
    Next
    INDEX
    Explanations

    regulation of

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

    The main thing this neuron does is detect the word “regulation” (and its close variants) in text.

    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
    s
    -1.78
    ’
    -1.77
    '
    -1.73
     zufrieden
    -1.70
     längere
    -1.65
    ⅗
    -1.63
     verbreitet
    -1.60
    几次
    -1.59
     zweif
    -1.52
     überrascht
    -1.52
    POSITIVE LOGITS
                    
    2.00
    ）
    1.79
     of
    1.77
    其
    1.73
     тысяч
    1.66
    ;
    1.63
    }
    1.63
    覈
    1.57
    缐
    1.55
    ”，
    1.55
    Activations Density 0.117%

    No Known Activations