© 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. 22-GEMMASCOPE-RES-131K
    7. 39387
    Prev
    Next
    INDEX
    Explanations

    affiliate, affiliated, affiliation

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

    This neuron activates on mentions of “affiliate” (and its morphological variants) in commercial or partnership contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     takže
    -2.69
    怏
    -2.45
     protože
    -2.41
     Of
    -2.28
     same
    -2.17
     dichos
    -2.17
     celles
    -2.14
     prioridad
    -2.13
     miesto
    -2.13
    身影
    -2.11
    POSITIVE LOGITS
    up
    2.38
    ୈ
    2.25
    𝐁
    2.22
     burbu
    2.20
     diego
    2.20
     cristo
    2.19
    “
    2.17
    h
    2.13
     gonzález
    2.13
    <bos>
    2.13
    Activations Density 0.013%

    No Known Activations