© 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. 71874
    Prev
    Next
    INDEX
    Explanations

    lag, lag time, lagging

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

    The neuron is activated by occurrences of the root “lag” (e.g. “lag,” “laggy,” “lagging”).

    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
    疍
    -2.67
    鉝
    -2.66
    剮
    -2.64
     dieß
    -2.61
    为什么会
    -2.58
    神
    -2.56
     休閒
    -2.56
    摃
    -2.55
    atação
    -2.45
    哢
    -2.42
    POSITIVE LOGITS
    =
    3.06
    M
    2.63
    );
    2.55
    '
    2.52
    O
    2.48
    b
    2.47
    ="
    2.42
    e
    2.39
    K
    2.38
    `
    2.33
    Activations Density 0.003%

    No Known Activations