© 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. 34-GEMMASCOPE-RES-131K
    7. 102647
    Prev
    Next
    INDEX
    Explanations

    expressing willingness

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

    The neuron fires on subject–auxiliary verb sequences (e.g. “people would be,” “they are willing”) that express willingness or conditional states.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    изнь
    -0.86
     Bab
    -0.75
    binant
    -0.69
    Garonne
    -0.68
    ldr
    -0.68
    baud
    -0.67
     перец
    -0.67
     angegebenen
    -0.65
    篷
    -0.64
    ഊ
    -0.64
    POSITIVE LOGITS
     willing
    7.00
     willingness
    5.88
    willing
    5.63
     Willing
    5.34
    Willing
    5.09
    愿意
    3.75
    願意
    3.44
     ready
    2.86
     unwilling
    2.81
     bereit
    2.81
    Activations Density 0.096%

    No Known Activations