© 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. 10-GEMMASCOPE-RES-131K
    4. 65285
    Prev
    Next
    INDEX
    Explanations

    reflecting on

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

    The neuron detects instances of reflective language—especially forms of the verb “reflect” (reflects, reflecting, reflection, reflected) and the accompanying “on.”

    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
    >
    -2.30
    </h1>
    -2.23
    就跟
    -2.19
     idyllic
    -2.06
     Another
    -2.05
     será
    -2.03
     are
    -2.02
     Here
    -1.97
     enfrentan
    -1.97
     Either
    -1.95
    POSITIVE LOGITS
     排骨
    2.25
    趼
    1.97
     插画
    1.85
    亖
    1.84
    這
    1.75
    岘
    1.75
    ᜀ
    1.70
    錞
    1.70
    ????????
    1.70
    なんだ
    1.70
    Activations Density 0.008%

    No Known Activations