© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48040
    Prev
    Next
    INDEX
    Explanations

    negotiating rates, deals, or outcomes

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

    The neuron activates on variants of the word “negotiate” (e.g. negotiate, negotiating, negotiation, negotiator).

    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
    2
    -3.55
    )
    -3.00
    /
    -2.67
    7
    -2.64
    ">
    -2.64
    ');
    -2.58
    t
    -2.56
     \"
    -2.56
    href
    -2.50
    hline
    -2.48
    POSITIVE LOGITS
    狆
    2.66
    
    2.63
    茘
    2.61
    涐
    2.61
    ↵
    2.53
    但却
    2.52
    枼
    2.50
     nguyen
    2.48
    lifter
    2.44
     纹身
    2.42
    Activations Density 0.003%

    No Known Activations