© 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. 22-GEMMASCOPE-RES-131K
    7. 16731
    Prev
    Next
    INDEX
    Explanations

    settle into a place or state

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

    This neuron fires on the verb “settle” (including its conjugated and phrasal forms like “settled down,” “settles in,” and “settled on”).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     estando
    -1.29
     вся
    -1.23
     incluida
    -1.14
    zemu
    -1.14
     they
    -1.13
     attraverso
    -1.09
     diversas
    -1.07
     quando
    -1.06
     diversos
    -1.05
     parteci
    -1.05
    POSITIVE LOGITS
     settles
    1.84
     settle
    1.61
     settled
    1.44
     Settle
    1.32
     with
    1.29
     settling
    1.27
     ‘
    1.17
    Settle
    1.15
     Behör
    1.14
    gencias
    1.13
    Activations Density 0.023%

    No Known Activations