© 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. 71444
    Prev
    Next
    INDEX
    Explanations

    some point in time

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

    The neuron flags vague temporal expressions—especially phrases like “at some point,” “at some time,” or “at some stage.”

    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
     maksi
    -2.13
    狆
    -2.08
     guapos
    -2.08
    鐒
    -1.95
     leksikon
    -1.92
    鷙
    -1.91
     面包
    -1.87
     髪型
    -1.87
     velg
    -1.84
    哢
    -1.84
    POSITIVE LOGITS
    ↵
    2.14
     протяжении
    1.99
    </u>
    1.86
    In
    1.84
    <em>
    1.84
     will
    1.76
     have
    1.74
     at
    1.70
    Also
    1.70
     many
    1.66
    Activations Density 0.005%

    No Known Activations