© 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. 34-GEMMASCOPE-RES-131K
    7. 59779
    Prev
    Next
    INDEX
    Explanations

    financial contributions and support

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

    This neuron identifies formal references to institutional funding or trust‐fund titles (e.g., “Local 282 Welfare, Pension, Annuity…Trust Funds,” “Annual Fund,” “Power Up PRS Technology Campaign”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     مدير
    -0.95
    Prob
    -0.82
     réaction
    -0.81
    ずら
    -0.81
    カス
    -0.80
     hermé
    -0.79
     ambienti
    -0.75
    illis
    -0.74
     ادار
    -0.73
     otten
    -0.72
    POSITIVE LOGITS
     fund
    1.63
     Fund
    1.41
     funds
    1.33
     scholarship
    1.18
     фон
    1.16
    基金
    1.15
     Scholarship
    1.11
     development
    1.07
     library
    1.02
     equipment
    1.02
    Activations Density 0.017%

    No Known Activations