© 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. 105133
    Prev
    Next
    INDEX
    Explanations

    peek inside or behind reveals

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

    The neuron responds to occurrences of the word “peek” (and its variants such as “peeking”) in the text.

    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
    鹇
    -2.63
    姈
    -2.53
    觔
    -2.50
     också
    -2.50
    ⚋
    -2.47
    呖
    -2.47
     Also
    -2.45
     say
    -2.41
    ikusbot
    -2.39
    溦
    -2.39
    POSITIVE LOGITS
    寕
    3.53
    sandalia
    3.39
    鬭
    2.88
    　　*
    2.78
    鄚
    2.64
    kemeja
    2.63
     jepang
    2.63
    Jangan
    2.61
    勠
    2.56
    嫱
    2.55
    Activations Density 0.001%

    No Known Activations