© 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. 128976
    Prev
    Next
    INDEX
    Explanations

    insurance company

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

    The neuron fires on mentions of insurers or payers (e.g. “insurance,” “company,” “payer”).

    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
     -
    -1.74
    </b>
    -1.59
     in
    -1.55
    与此同时
    -1.55
     '
    -1.51
    </sup>
    -1.48
    各类
    -1.45
    不管是
    -1.41
    </h4>
    -1.39
    但他
    -1.38
    POSITIVE LOGITS
     ſch
    1.84
    棡
    1.72
     occuper
    1.70
     considerare
    1.70
     dijeron
    1.66
    喁
    1.61
    できます
    1.60
    ︕
    1.60
    のが
    1.55
     Nomor
    1.55
    Activations Density 0.027%

    No Known Activations