© 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. 48060
    Prev
    Next
    INDEX
    Explanations

    concerned parties and interest

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

    This neuron detects mentions of formal participants or stakeholders in legal or official documents (e.g. “signatories,” “parties”).

    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
    .
    -2.91
    $
    -2.25
     —
    -2.23
    [
    -1.98
    {
    -1.94
    <em>
    -1.83
    ’
    -1.81
     “
    -1.78
    <
    -1.74
    <0xF0>
    -1.70
    POSITIVE LOGITS
     entanto
    1.91
    鹟
    1.82
    ㌧
    1.82
    Karakteristik
    1.81
    Kegiatan
    1.80
    鸫
    1.73
    łyż
    1.72
    貽
    1.71
    桄
    1.70
    鈈
    1.69
    Activations Density 0.012%

    No Known Activations