© 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. 75173
    Prev
    Next
    INDEX
    Explanations

    years in contracts and deals

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

    The neuron fires on expressions that specify a time-length or term—especially number-of-years phrases like “five-year,” “two-year,” “a year,” etc.

    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
     ouvir
    -1.16
     intuiti
    -1.04
     levering
    -1.02
     unik
    -0.98
     esquecer
    -0.97
     responsabilità
    -0.97
    humanité
    -0.96
     picioare
    -0.93
     affez
    -0.93
    Coordonnées
    -0.93
    POSITIVE LOGITS
     boyunca
    1.05
    新竹
    1.01
     At
    0.94
     NM
    0.94
     That
    0.94
    L
    0.93
     perspective
    0.93
     Brazilian
    0.92
    下来
    0.92
    ributo
    0.92
    Activations Density 0.042%

    No Known Activations