© 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. 34-GEMMASCOPE-RES-131K
    7. 90267
    Prev
    Next
    INDEX
    Explanations

    customer service inquiries

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

    This neuron strongly responds to auxiliary verbs and participles used in passive‐voice technical or procedural phrasing (e.g. “are,” “being,” “having,” “is determined”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ​
    -1.13
     pretty
    -1.12
     allerlei
    -1.11
    ském
    -1.04
    好吃
    -1.02
    ₀
    -1.00
    ponym
    -0.99
     hope
    -0.96
    Pretty
    -0.96
     먹
    -0.96
    POSITIVE LOGITS
    NOTE
    1.34
     product
    1.19
    ınız
    1.16
    ଶ
    1.12
     customer
    1.11
     Customer
    1.09
     your
    1.09
    ⼿
    1.09
    🆅
    1.07
    your
    1.05
    Activations Density 0.045%

    No Known Activations