© 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. 111185
    Prev
    Next
    INDEX
    Explanations

    list of things to do

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

    This neuron fires on list-like or queue-like markers—that is, words and phrases indicating items in a task/to-do list or positions in a processing queue.

    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
    6
    -1.55
    3
    -1.45
    9
    -1.35
    Got
    -1.31
    Top
    -1.18
     tajam
    -1.13
    Did
    -1.10
                                   
    -1.10
    <0xEF>
    -1.09
    The
    -1.09
    POSITIVE LOGITS
    quelize
    1.39
     so
    1.29
    ريف
    1.21
    懣
    1.19
     หนัง
    1.18
    Их
    1.18
    *~*~
    1.16
    Ehrungen
    1.16
     bateria
    1.15
     RAILWAY
    1.14
    Activations Density 0.064%

    No Known Activations