© 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. 129243
    Prev
    Next
    INDEX
    Explanations

    events and their implications

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

    This neuron responds to words that denote major events or transactions—terms like sale, deal, move, loss, win, death, passing, transaction.

    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
     tirs
    -1.59
     dezelve
    -1.59
     soldat
    -1.53
     ſmall
    -1.52
     contextes
    -1.52
     tille
    -1.51
     lage
    -1.50
     fald
    -1.47
     alfo
    -1.42
     colonnes
    -1.42
    POSITIVE LOGITS
     will
    2.05
     may
    1.72
     might
    1.69
     what
    1.63
     would
    1.59
    What
    1.52
     time
    1.48
    what
    1.46
     could
    1.46
     gave
    1.43
    Activations Density 0.061%

    No Known Activations