© 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. 98709
    Prev
    Next
    INDEX
    Explanations

    motion propelled through air or space

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

    The neuron activates on descriptions of things (people or objects) being forcefully propelled, thrown, or blown through the air.

    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
     on
    -1.48
     see
    -1.38
     více
    -1.37
     pouring
    -1.29
     difícil
    -1.28
     nowych
    -1.27
     entsprechenden
    -1.27
     naše
    -1.27
    .”
    -1.25
     liaison
    -1.25
    POSITIVE LOGITS
    彼は
    1.42
     dată
    1.34
    Amérique
    1.30
    鲼
    1.29
    鲥
    1.29
    ād
    1.27
     chilen
    1.27
     Servers
    1.26
     lieux
    1.25
    Australie
    1.25
    Activations Density 0.043%

    No Known Activations