© 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. 22508
    Prev
    Next
    INDEX
    Explanations

    Be sure to

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

    This neuron detects imperative/advisory cue phrases—most prominently the “be sure to” instruction construction.

    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
    ()}
    -1.80
     all
    -1.72
     a
    -1.71
    》，
    -1.70
     so
    -1.63
    ↵↵
    -1.59
     beendet
    -1.56
     нержа
    -1.54
     what
    -1.53
    水晶
    -1.53
    POSITIVE LOGITS
     also
    2.50
    也要
    2.11
    訁
    2.03
    also
    1.95
     cũng
    1.84
    their
    1.83
    including
    1.82
    注意事
    1.76
    having
    1.75
    出てくる
    1.74
    Activations Density 0.006%

    No Known Activations