© 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. 15443
    Prev
    Next
    INDEX
    Explanations

    non-

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

    The neuron activates strongly on words that are part of a “non‐X” construction—that is, terms immediately following the negating prefix “non-.”

    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
     trasforma
    -1.27
     or
    -1.24
     висо
    -1.16
    jgl
    -1.16
     или
    -1.12
     out
    -1.12
     吗
    -1.12
     नहीं
    -1.09
    న్
    -1.09
     alebo
    -1.07
    POSITIVE LOGITS
     incluindo
    1.33
     mą
    1.23
    iation
    1.17
     endeavor
    1.17
    Več
    1.16
    peč
    1.13
     unique
    1.13
     you
    1.12
    nological
    1.09
     jego
    1.09
    Activations Density 0.080%

    No Known Activations