© 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. 34-GEMMASCOPE-RES-131K
    7. 117165
    Prev
    Next
    INDEX
    Explanations

    expiration and expiry dates

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

    text related to contract expirations or renewals and when they occur.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to past-participle verb forms (especially in passive constructions).

    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
     retreats
    -0.86
     significados
    -0.82
    History
    -0.80
    cleaned
    -0.79
     início
    -0.78
    Rollback
    -0.77
    Travel
    -0.77
    把自己
    -0.77
     "@/
    -0.76
    vement
    -0.75
    POSITIVE LOGITS
     expiration
    2.59
     expired
    2.56
     expiring
    2.13
     expiry
    2.09
     expire
    2.05
     expir
    1.81
    expired
    1.71
     expires
    1.68
    Expired
    1.67
    Expiration
    1.66
    Activations Density 0.034%

    No Known Activations