© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119589
    Prev
    Next
    INDEX
    Explanations

    "be a" or "is a"

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

    This neuron activates on the start of embedded “what” clauses—phrases beginning with “what is a…” or “what must have been…”

    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
     of
    -2.27
    what
    -1.87
    What
    -1.79
     in
    -1.76
    h
    -1.69
     after
    -1.67
     at
    -1.64
     what
    -1.62
    r
    -1.59
    your
    -1.59
    POSITIVE LOGITS
     a
    2.31
     ráp
    1.79
     Affaires
    1.67
     hormigón
    1.62
     rése
    1.60
    页面存档备份
    1.60
     bén
    1.58
     acoged
    1.55
    دکتر
    1.52
     rác
    1.51
    Activations Density 0.019%

    No Known Activations