© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 165
    Prev
    Next
    INDEX
    Explanations

    reading and spelling practice

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

    The neuron fires on infinitive‐phrase descriptions of classroom or learning activities (e.g. “to read to children,” “activities to work with pirates,” “a new sound is introduced with a story”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     if
    -1.11
     へ
    -1.06
     ancak
    -1.05
    了一口
    -1.03
     الصيف
    -1.02
     المعد
    -1.00
    ִּ
    -0.99
     الحكوم
    -0.98
     يول
    -0.98
     чего
    -0.97
    POSITIVE LOGITS
     teaches
    1.32
     ļoti
    1.29
     teaching
    1.20
     learning
    1.19
     χρησιμοποι
    1.16
     bēr
    1.16
    ïti
    1.15
     preescolar
    1.15
     children
    1.13
    特急
    1.13
    Activations Density 0.031%

    No Known Activations