© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100150
    Prev
    Next
    INDEX
    Explanations

    commission payments

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

    The neuron activates whenever the text contains the word “commission” (or its morphological variants like “commissions” or “commissioned”).

    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
    𖣘
    -3.00
    眎
    -2.91
    樒
    -2.89
     uſed
    -2.75
    ᠂
    -2.64
    硨
    -2.61
    媜
    -2.59
     endured
    -2.56
     recommended
    -2.53
     continually
    -2.52
    POSITIVE LOGITS
    ↵
    3.64
    </h4>
    2.72
    ),
    2.52
    -
    2.50
    ↵↵↵↵↵↵↵↵↵↵↵↵
    2.47
    </sup>
    2.39
    ).
    2.28
    但是在
    2.22
    ться
    2.22
    n
    2.19
    Activations Density 0.019%

    No Known Activations