© 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. 6956
    Prev
    Next
    INDEX
    Explanations

    movement prepositions to destinations

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

    This neuron specifically fires on occurrences of the word “out.”

    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
     дорогой
    -1.59
    </h3>
    -1.56
    猻
    -1.55
     можешь
    -1.54
    さり
    -1.54
    ซึ่ง
    -1.53
    isesta
    -1.52
    gelegt
    -1.51
     perros
    -1.50
    unuz
    -1.50
    POSITIVE LOGITS
     {
    2.06
     None
    1.95
     We
    1.84
    MessageTagHelper
    1.80
     â
    1.80
     Our
    1.78
    旅程
    1.73
     acuarela
    1.67
     Some
    1.64
     aim
    1.61
    Activations Density 0.003%

    No Known Activations