© 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. 73498
    Prev
    Next
    INDEX
    Explanations

    affiliate marketing programs

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

    The neuron fires strongly on affiliate‐marketing and promotional link jargon (e.g. “affiliate,” tracking IDs, ad network references).

    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
     lainnya
    -1.26
    "
    -1.23
     Gegenteil
    -1.20
     fantaisie
    -1.09
    原材料
    -1.07
     أخرى
    -1.05
    Price
    -1.02
    In
    -1.02
     boken
    -1.02
    Green
    -0.99
    POSITIVE LOGITS
     THEIR
    1.36
     souligne
    1.31
    svet
    1.27
    Krank
    1.26
     asegurarse
    1.25
    meteries
    1.23
     protège
    1.21
    𓋼
    1.20
    龃
    1.20
    ৳
    1.20
    Activations Density 0.045%

    No Known Activations