© 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. 72115
    Prev
    Next
    INDEX
    Explanations

    other side, other son

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

    The neuron strongly activates on occurrences of the word “other” (and its close variants like “others” or “difference” in the sense of “otherness”).

    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
    ↵
    -1.59
     owner
    -1.41
     optimism
    -1.35
    其他人
    -1.35
     If
    -1.35
    .
    -1.30
    Global
    -1.27
    -1.27
    负责人
    -1.27
     deportivas
    -1.27
    POSITIVE LOGITS
    UAGES
    1.62
    вають
    1.62
    getJSONArray
    1.59
     dengue
    1.55
     всѣ
    1.55
     ‘‘
    1.53
    (^_^
    1.51
    鬘
    1.50
    ://$
    1.50
     complimented
    1.50
    Activations Density 0.022%

    No Known Activations