© 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. 58077
    Prev
    Next
    INDEX
    Explanations

    specific contrasts

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

    The neuron fires on prominent technical or medical topic nouns (and related quantitative terms) that usually signal key subjects or metrics in academic writing.

    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
     and
    -1.28
     bizony
    -1.05
     not
    -1.05
    zeption
    -1.05
     zarówno
    -1.02
    坚定
    -1.01
    厛
    -1.01
    renewcommand
    -1.01
     Dinas
    -0.98
     וב
    -0.97
    POSITIVE LOGITS
     推薦
    1.22
    ="")
    1.20
    之处
    1.17
     poffible
    1.14
    idey
    1.13
    ğe
    1.12
     術
    1.07
     than
    1.07
     贈
    1.06
     to
    1.05
    Activations Density 0.271%

    No Known Activations