© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80734
    Prev
    Next
    INDEX
    Explanations

    business and market concepts

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

    The neuron flags terms related to commercial or business/economic contexts (e.g. market, business, industry, company, commercial, programme).

    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
    擼
    -1.61
     they
    -1.38
    łóż
    -1.33
    槤
    -1.30
    >--}}
    -1.26
    气氛
    -1.25
     conservación
    -1.24
    *{
    -1.24
    ardez
    -1.24
    <td>
    -1.23
    POSITIVE LOGITS
    0
    1.52
     yılı
    1.24
     però
    1.21
     These
    1.21
    廛
    1.19
     yaşında
    1.16
     ใน
    1.13
    サイズは
    1.13
    떄
    1.13
     brutal
    1.11
    Activations Density 0.360%

    No Known Activations