© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    will/would/会/就会/会出现

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

    The neuron detects modal verbs and markers of future or hypothetical actions (e.g. “will,” “would,” and Chinese “会”).

    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
    tu
    -1.53
    ar
    -1.50
    maire
    -1.45
     flimsy
    -1.45
    ia
    -1.45
    ATORY
    -1.43
     одной
    -1.42
    TITUDE
    -1.41
    ca
    -1.41
    刄
    -1.37
    POSITIVE LOGITS
     a
    1.52
    {
    1.41
    );
    1.35
    OREM
    1.34
     Quelques
    1.26
    )",
    1.23
     Vorteil
    1.22
     eventually
    1.21
     myös
    1.19
    ープン
    1.19
    Activations Density 0.009%

    No Known Activations