© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39779
    Prev
    Next
    INDEX
    Explanations

    yet another

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

    The neuron strongly activates on occurrences of the word “yet.”

    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
    $,
    -2.86
    ”,
    -2.84
    )$
    -2.81
    枼
    -2.78
    蠃
    -2.70
    Ꝑ
    -2.61
    挲
    -2.56
     juicy
    -2.55
    ㌧
    -2.47
    𖥧
    -2.47
    POSITIVE LOGITS
    寕
    3.08
    ’
    3.05
    %$$
    2.83
    '
    2.80
    The
    2.72
     ajuda
    2.66
    That
    2.64
    
    2.64
    ſelf
    2.63
    𖣘
    2.63
    Activations Density 0.014%

    No Known Activations