© 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. 45370
    Prev
    Next
    INDEX
    Explanations

    more and Yue names

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

    The neuron strongly responds to the comparative adverb “more,” especially in correlative phrases like “the more … the more.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.47
    }$.
    -1.78
     justifiable
    -1.77
    驺
    -1.70
    )$
    -1.70
    辔
    -1.65
    柺
    -1.63
    </em>
    -1.59
    >
    -1.59
    壆
    -1.56
    POSITIVE LOGITS
    </h1>
    1.91
     \
    1.80
    媃
    1.76
     一
    1.70
    poň
    1.59
     they
    1.57
    会
    1.56
    <bos>
    1.56
    they
    1.54
    APPING
    1.52
    Activations Density 0.002%

    No Known Activations