© 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. 47729
    Prev
    Next
    INDEX
    Explanations

    ceased or stopped working

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

    The neuron flags phrases that express cessation—i.e. when something “ceases to exist” or stops functioning.

    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
     parachoque
    -2.61
    ᆞ
    -2.39
    鹇
    -2.36
     火鍋
    -2.34
    脔
    -2.31
     墊
    -2.25
     纹身
    -2.22
    Ꮂ
    -2.20
    ーズン
    -2.16
     ecran
    -2.16
    POSITIVE LOGITS
     /
    2.22
     for
    2.22
     —
    2.06
    if
    2.03
     I
    2.03
    D
    2.00
    ,
    1.99
     &
    1.98
    m
    1.94
     be
    1.93
    Activations Density 0.005%

    No Known Activations