© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    identifying "like to"

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

    This neuron specializes in spotting polite request phrases, especially “would like (to)….”

    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
    with
    -3.20
    to
    -2.98
    1
    -2.73
    It
    -2.61
    The
    -2.44
    籏
    -2.39
    When
    -2.28
    媖
    -2.27
     現在
    -2.27
    袮
    -2.23
    POSITIVE LOGITS
     something
    2.28
    犼
    2.17
     interessante
    2.13
     queridos
    2.05
     mooie
    2.03
     andere
    2.00
     animaux
    1.97
     restes
    1.97
    鼋
    1.95
     puis
    1.94
    Activations Density 0.022%

    No Known Activations