© 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. 99731
    Prev
    Next
    INDEX
    Explanations

    transaction types or settings

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

    The neuron fires on the literal string “transact” (as in transaction, transactional, transactionally, etc.) whenever that substring appears.

    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
     ボール
    -1.22
     dreary
    -1.21
     potrà
    -1.20
     delineated
    -1.15
     forlorn
    -1.09
     !!!!!
    -1.09
     fantastic
    -1.09
     disgruntled
    -1.06
     spectacular
    -1.05
     adorned
    -1.05
    POSITIVE LOGITS
     unusually
    1.18
     Transaction
    1.17
     moderately
    1.14
    ưở
    1.14
     supremely
    1.13
     Putting
    1.05
     extraordinarily
    1.05
    مة
    1.04
    alism
    1.04
     biggest
    1.03
    Activations Density 0.007%

    No Known Activations