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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40209
    Prev
    Next
    INDEX
    Explanations

    what is questions

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

    The neuron fires on the copula “is” (especially in “What is…” question headings), marking where a definition‐style question is being asked.

    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
     somewhat
    -2.52
    ").
    -2.36
    很少
    -2.34
    ;
    -2.34
     dismal
    -2.28
     decidedly
    -2.25
     exceedingly
    -2.23
     lauded
    -2.22
    ""
    -2.19
    歺
    -2.19
    POSITIVE LOGITS
     this
    2.56
     an
    2.08
     exquisitely
    1.91
     facilitate
    1.88
     alleviate
    1.86
     Surprisingly
    1.84
     some
    1.82
     exquisite
    1.82
     facilitates
    1.80
     burgeoning
    1.80
    Activations Density 0.037%

    No Known Activations