© 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. 42278
    Prev
    Next
    INDEX
    Explanations

    recyclable, Bezos, magician, IOT

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

    The neuron activates on mentions of recyclability—i.e. the term “recyclable” (even when split across subword tokens).

    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
    “
    -2.92
    ية
    -2.75
    ჻
    -2.53
    or
    -2.48
     прошлом
    -2.45
     \%$
    -2.34
    ☫
    -2.23
    л
    -2.17
    ⭏
    -2.14
    o
    -2.13
    POSITIVE LOGITS
    '
    2.75
    ðsíða
    2.64
    tigung
    2.48
    赂
    2.47
    遹
    2.41
    鈇
    2.38
     zowel
    2.31
    可以说
    2.27
     جدید
    2.27
     blijkt
    2.25
    Activations Density 0.012%

    No Known Activations