© 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. 48682
    Prev
    Next
    INDEX
    Explanations

    getting married

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

    The neuron activates on numeric tokens—especially multi‐digit date and year numbers.

    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
     wife
    -0.88
     razon
    -0.86
     esposa
    -0.84
     wives
    -0.82
    wife
    -0.82
     Wives
    -0.81
     extraño
    -0.81
     Versions
    -0.80
     versão
    -0.79
     husband
    -0.78
    POSITIVE LOGITS
     united
    1.45
     unites
    1.37
     unite
    1.31
     uniting
    1.29
     union
    1.13
    union
    1.03
     объеди
    0.99
    Union
    0.96
    united
    0.95
     unions
    0.93
    Activations Density 0.015%

    No Known Activations