© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    carrying and handles

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

    The neuron fires on words naming or describing carrying and transport (especially of drinks)—for example “carry,” “tray,” “takeaway,” “transporting,” and related container/carrier terms.

    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
    autoreleasepool
    -1.15
    他们的
    -1.13
    toCharArray
    -1.12
     बदल
    -1.10
     amado
    -1.10
    』。
    -1.09
    шна
    -1.06
    </h1>
    -1.05
     there
    -1.04
     musik
    -1.04
    POSITIVE LOGITS
    狃
    1.20
     picnics
    1.10
    窒
    1.10
    ۟
    1.10
    CHRE
    1.09
    textsc
    1.09
     verksam
    1.07
    TONE
    1.06
    affiche
    1.05
    Italie
    1.05
    Activations Density 0.040%

    No Known Activations