© 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. 130141
    Prev
    Next
    INDEX
    Explanations

    future events

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

    This neuron detects temporal-proximity phrases, such as “near future” or “recent past.”

    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
    鐒
    -1.91
    %");
    -1.83
    ^^^^^^^^
    -1.77
    勛
    -1.69
    擄
    -1.68
    䴀
    -1.68
     "/")
    -1.67
    譏
    -1.66
    蛩
    -1.65
    戆
    -1.64
    POSITIVE LOGITS
     '
    2.36
     
    2.08
    c
    1.90
    j
    1.71
    1
    1.70
     If
    1.70
     "
    1.68
    b
    1.66
    "
    1.65
    4
    1.65
    Activations Density 0.014%

    No Known Activations