© 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. 105554
    Prev
    Next
    INDEX
    Explanations

    affiliate links and compensation

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

    The neuron detects sections of text that disclose affiliate links or other monetization and compensation statements.

    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
     during
    -1.74
     three
    -1.67
     for
    -1.49
     five
    -1.41
     four
    -1.39
     even
    -1.38
     with
    -1.34
     required
    -1.34
     six
    -1.29
     протягом
    -1.28
    POSITIVE LOGITS
     اینجا
    1.26
     hyster
    1.25
    ícias
    1.23
     JAXBElement
    1.20
    ネル
    1.20
     أعلى
    1.19
     ſever
    1.19
     Siehe
    1.17
     тут
    1.15
     hysteria
    1.15
    Activations Density 0.163%

    No Known Activations