© 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. 74368
    Prev
    Next
    INDEX
    Explanations

    issuing orders and commands

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

    The neuron activates on words and phrases that denote issuing or following commands (e.g. “orders,” “instructed,” “gave orders”).

    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
    下一篇
    -1.86
    <bos>
    -1.85
     wußte
    -1.83
     瓶
    -1.83
     glaubte
    -1.66
    ᅠ
    -1.63
     endDate
    -1.63
    鳢
    -1.61
    宝石
    -1.60
    borderSide
    -1.60
    POSITIVE LOGITS
     to
    2.05
     cihaz
    2.00
     about
    1.91
    隳
    1.85
    なるべく
    1.84
     felicitación
    1.75
    ING
    1.73
     pimpinan
    1.71
     роки
    1.68
     order
    1.67
    Activations Density 0.027%

    No Known Activations