© 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. 72254
    Prev
    Next
    INDEX
    Explanations

    verbs initiating actions

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

    The neuron fires on imperative‐mood verbs (command/action words) that open instructional or how‐to statements.

    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
    CAPITULO
    -1.90
     또
    -1.74
    ↵↵↵
    -1.69
     
    -1.67
    CAPÍTULO
    -1.65
     território
    -1.64
     imóvel
    -1.59
    总会
    -1.59
     edifício
    -1.59
    OBJETIVO
    -1.56
    POSITIVE LOGITS
     your
    3.02
     yourself
    2.58
     or
    2.06
     in
    1.95
     if
    1.92
     been
    1.80
     them
    1.79
     összefoglal
    1.68
     an
    1.68
     尔
    1.64
    Activations Density 0.500%

    No Known Activations