© 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. 19897
    Prev
    Next
    INDEX
    Explanations

    schedule, feeding, expenses, date

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

    This neuron detects imperative instruction words (i.e. commands) marking list-item tips or advice.

    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
     then
    -1.39
     VARIOUS
    -1.35
     leurs
    -1.29
     цвят
    -1.27
    뗄
    -1.24
     pleaf
    -1.23
     hien
    -1.22
     hond
    -1.22
     moft
    -1.21
    ᠴ
    -1.20
    POSITIVE LOGITS
     your
    2.42
     include
    1.54
     new
    1.52
     if
    1.49
     Use
    1.35
     including
    1.33
     use
    1.32
     To
    1.32
    它的
    1.31
     when
    1.30
    Activations Density 0.149%

    No Known Activations