© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15344
    Prev
    Next
    INDEX
    Explanations

    preparing for an event

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

    The neuron fires on imperative “get ready to/prepare to”–style calls to action introducing what follows.

    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
    s
    -2.16
     can
    -2.06
     if
    -1.88
     would
    -1.73
    ).
    -1.73
     For
    -1.70
     new
    -1.66
     When
    -1.63
     its
    -1.61
     when
    -1.60
    POSITIVE LOGITS
     唯美
    1.68
     coloris
    1.66
     内衣
    1.65
     特写
    1.64
     拌
    1.61
     listes
    1.60
     髪型
    1.59
     horloge
    1.55
     短发
    1.55
    kamen
    1.54
    Activations Density 0.012%

    No Known Activations