© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68692
    Prev
    Next
    INDEX
    Explanations

    prefer to + verb

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

    The neuron activates on the phrase “prefer to,” detecting expressions of personal preference.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </b>
    -1.73
    沨
    -1.70
     oppression
    -1.58
     BOTH
    -1.54
     Klicken
    -1.52
     múltiples
    -1.51
     sugiere
    -1.51
    навли
    -1.51
    푢
    -1.46
     recomienda
    -1.45
    POSITIVE LOGITS
    ↵
    1.99
    這
    1.61
     會
    1.51
    这种
    1.50
    $
    1.48
    type
    1.48
    When
    1.48
    ))$_
    1.44
     antonio
    1.42
     leone
    1.42
    Activations Density 0.004%

    No Known Activations