© 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. 8617
    Prev
    Next
    INDEX
    Explanations

    since then

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

    This neuron detects temporal adverbs and discourse markers (words like “ever,” “then,” “since,” etc.) that signal time or continuity.

    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
    欵
    -1.59
     Eigentümer
    -1.55
     naše
    -1.54
     with
    -1.52
    看一下
    -1.51
    汌
    -1.50
    ilustrasi
    -1.50
    晅
    -1.49
     and
    -1.48
     an
    -1.47
    POSITIVE LOGITS
    。「
    1.77
    她
    1.72
    🤨
    1.70
     ;
    1.70
    。
    1.68
    で
    1.64
    😤
    1.64
    s
    1.61
    );
    1.59
     $)$
    1.59
    Activations Density 0.032%

    No Known Activations