© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66684
    Prev
    Next
    INDEX
    Explanations

    pleading or begging for something

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

    The main thing this neuron does is find instances of earnest requests or pleas (e.g., “beg,” “plead,” “implore”).

    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
     ‘
    -1.63
                    
    -1.57
    ၞ
    -1.54
        
    -1.52
    ческих
    -1.50
     tarko
    -1.50
    一月
    -1.48
     ४
    -1.46
     such
    -1.45
                   
    -1.44
    POSITIVE LOGITS
    ჻
    1.70
     але
    1.69
    8
    1.66
     kobieta
    1.63
     тази
    1.59
     في
    1.57
    IA
    1.57
    
    1.56
    岽
    1.54
    ſſel
    1.53
    Activations Density 0.012%

    No Known Activations