© 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. 22-GEMMASCOPE-RES-131K
    7. 75066
    Prev
    Next
    INDEX
    Explanations

    yet followed by contrast

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

    This neuron activates on the adversative conjunction “Yet,” marking contrastive or surprising turn-taking 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_22/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
    蠃
    -2.34
    ㌧
    -2.25
    ↵↵
    -2.13
    聍
    -2.09
    $,
    -2.03
    ”,
    -2.02
    فیلم
    -2.02
    枼
    -1.99
    
    -1.98
    珰
    -1.96
    POSITIVE LOGITS
    ’
    3.42
    '
    2.39
    "
    2.39
    %$$
    2.36
    falfa
    2.34
    They
    2.30
    寕
    2.28
    quirrel
    2.25
     ajuda
    2.23
    CHREIB
    2.19
    Activations Density 0.014%

    No Known Activations