© 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. 66785
    Prev
    Next
    INDEX
    Explanations

    taking up a new activity

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

    The neuron fires on occurrences of the phrasal verb “take up” (and its inflected forms such as “took up” or “taking up”).

    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
    {
    -2.44
    .
    -2.34
     {
    -2.05
     två
    -1.67
    ICOLON
    -1.66
     then
    -1.63
    (
    -1.60
    ↵
    -1.60
     sublime
    -1.56
    '
    -1.55
    POSITIVE LOGITS
    .”
    1.95
     Also
    1.70
     цветами
    1.66
    ?”
    1.63
     décédé
    1.58
    because
    1.56
    नलोड
    1.55
    具体的
    1.53
     monstruo
    1.53
    безпе
    1.52
    Activations Density 0.006%

    No Known Activations