© 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. 64385
    Prev
    Next
    INDEX
    Explanations

    disability assessment questionnaires

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

    The neuron strongly activates on mentions of clinical measurement instruments, scales, or indices (e.g. questionnaire names and outcome‐measure 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     правительства
    -1.23
    ϒ
    -1.22
     Knie
    -1.22
     we
    -1.20
    之事
    -1.18
     الحكومة
    -1.17
    lamy
    -1.15
    g
    -1.12
    齑
    -1.11
     jedoch
    -1.09
    POSITIVE LOGITS
     assessment
    1.55
    TokenNameRPAREN
    1.55
    hdysval
    1.53
    ֶּ
    1.49
     questionnaire
    1.49
    Teraz
    1.49
     кроссовки
    1.48
    batterie
    1.47
    niña
    1.46
     rating
    1.44
    Activations Density 0.273%

    No Known Activations