© 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. 41336
    Prev
    Next
    INDEX
    Explanations

    not yet

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

    This neuron strongly activates on occurrences of the word "yet," especially when used as an adverb indicating something is not known or completed.

    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
    いきましょう
    -1.52
    менту
    -1.48
     tí
    -1.48
    挲
    -1.46
     premiere
    -1.46
    cookieParser
    -1.45
     uren
    -1.45
    枼
    -1.44
     vik
    -1.44
    lgari
    -1.43
    POSITIVE LOGITS
    ’
    1.92
     begun
    1.73
    ！！”
    1.70
    hoenix
    1.59
    '
    1.58
    服务的
    1.55
     ”
    1.53
    ,”
    1.52
     artísticas
    1.52
     see
    1.50
    Activations Density 0.013%

    No Known Activations