© 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. 34-GEMMASCOPE-RES-131K
    7. 1675
    Prev
    Next
    INDEX
    Explanations

    at a

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

    This neuron detects temporal phrases that reference a specific point in time, like “at a moment’s notice” or “at a given moment.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     a
    -1.27
     tabac
    -0.93
    衛隊
    -0.91
     खरीदा
    -0.91
    方針
    -0.91
     ۹
    -0.90
     japon
    -0.90
    鍮
    -0.87
     Estes
    -0.86
     tane
    -0.86
    POSITIVE LOGITS
     given
    1.10
     standstill
    0.97
     later
    0.96
     conclusão
    0.96
     nearby
    0.95
    たびに
    0.93
    ようです
    0.92
     reasonable
    0.92
    ときの
    0.92
     whim
    0.90
    Activations Density 0.055%

    No Known Activations