© 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. 59802
    Prev
    Next
    INDEX
    Explanations

    third-party

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

    The neuron strongly activates on mentions of “third-party” (or “third party”) in text.

    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
    1
    -0.91
     second
    -0.88
    できるように
    -0.88
     powin
    -0.85
     quantità
    -0.84
     persönlich
    -0.84
    のお客様
    -0.82
    inspiring
    -0.81
     apont
    -0.81
    助理
    -0.81
    POSITIVE LOGITS
     vendor
    1.18
    party
    1.15
    开发者
    1.11
     dealings
    1.07
     logistics
    1.07
     vendors
    0.99
    whom
    0.98
    itore
    0.98
    ▬▬▬▬
    0.98
     gare
    0.97
    Activations Density 0.013%

    No Known Activations