© 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. 67994
    Prev
    Next
    INDEX
    Explanations

    contract duration or scholarship

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

    This neuron detects mentions of signing or extending contracts, including terms and durations (e.g., “signed a two-year deal,” “penned a new long-term contract”).

    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
    v
    -1.07
    H
    -1.07
    ÍAS
    -1.05
    甚至是
    -1.05
    N
    -1.01
     utiliza
    -1.00
    定制
    -0.99
     उदाहरण
    -0.98
    b
    -0.98
     deliver
    -0.97
    POSITIVE LOGITS
     contract
    1.37
     contracts
    1.27
     水墨
    1.24
    硯
    1.23
     avenir
    1.21
     estampado
    1.20
     contrato
    1.20
     régiment
    1.18
     transparan
    1.18
     InputStream
    1.17
    Activations Density 0.018%

    No Known Activations