© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40261
    Prev
    Next
    INDEX
    Explanations

    recent updates and releases

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

    The neuron activates on mentions of things being recent or most recent (e.g. “recent,” “most recent,” often paired with data or events).

    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
    ',
    -2.11
    举动
    -1.83
    щей
    -1.81
    {
    -1.79
     maroon
    -1.74
     opti
    -1.73
    :@"
    -1.65
    On
    -1.61
     creeps
    -1.59
    "]));
    -1.56
    POSITIVE LOGITS
    眛
    2.38
     addition
    2.06
     our
    1.98
     pesso
    1.94
    蠵
    1.91
    髕
    1.88
    珖
    1.88
    ⑾
    1.81
    一旁的
    1.80
     dê
    1.80
    Activations Density 0.007%

    No Known Activations