© 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. 114089
    Prev
    Next
    INDEX
    Explanations

    small parts or quantities

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

    The neuron fires on instances of the adjective “small” (especially when it’s used to introduce or describe a noun phrase like “small part,” “small program,” “small section,” etc.).

    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
    .
    -1.72
    to
    -1.55
     memutus
    -1.53
    <b>
    -1.52
    iações
    -1.45
    “
    -1.42
     Where
    -1.41
    <blockquote>
    -1.41
    ll
    -1.37
                   
    -1.36
    POSITIVE LOGITS
    憷
    2.09
    𓂅
    1.87
    関連リンク
    1.78
    うれしい
    1.73
     décision
    1.70
    噘
    1.66
    将她
    1.65
     capilla
    1.63
    她们
    1.61
    诋
    1.61
    Activations Density 0.021%

    No Known Activations