© 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. 22545
    Prev
    Next
    INDEX
    Explanations

    plur. nouns ending in ges

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

    This neuron activates on mentions of “midge” (especially “midges” or taxonomic names containing “midge”), i.e., occurrences of that insect name.

    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
    泔
    -2.95
    鸶
    -2.86
    酲
    -2.80
    骉
    -2.70
    奩
    -2.56
     groots
    -2.53
    唞
    -2.52
    Ꭳ
    -2.48
    脔
    -2.47
    蛩
    -2.45
    POSITIVE LOGITS
    y
    4.34
    s
    3.28
    的
    2.91
    ges
    2.75
    也有
    2.53
     стал
    2.47
    みたら
    2.38
     где
    2.31
    8
    2.28
     あります
    2.25
    Activations Density 0.006%

    No Known Activations