© 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. 6911
    Prev
    Next
    INDEX
    Explanations

    qualitatively, accurately, intended

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

    The neuron fires on longer, morphologically complex content words (e.g. multi-syllable adjectives/adverbs/nouns), effectively picking out “long” words.

    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
     all
    -2.03
     whose
    -1.54
     will
    -1.46
     $(
    -1.45
     have
    -1.41
     out
    -1.38
    quième
    -1.37
     January
    -1.36
     whom
    -1.36
     has
    -1.35
    POSITIVE LOGITS
    他の
    1.59
     considération
    1.58
     ſtre
    1.50
     alemanes
    1.48
     giorgio
    1.48
    オリーブ
    1.48
    做一个
    1.47
    ︕
    1.46
     unicornio
    1.45
    鮰
    1.45
    Activations Density 0.121%

    No Known Activations