© 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. 71394
    Prev
    Next
    INDEX
    Explanations

    surviving veteran died

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

    The neuron primarily activates on numeric tokens representing dates or years.

    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
    :
    -1.05
    ຣ
    -1.05
     Snackbar
    -0.95
    те
    -0.92
    Transformer
    -0.91
     caverns
    -0.87
    newNode
    -0.86
     рабо
    -0.86
    Rt
    -0.84
    Diana
    -0.83
    POSITIVE LOGITS
     elderly
    1.38
     centen
    1.25
     surviving
    1.20
     idade
    1.16
     still
    1.16
     age
    1.16
     aged
    1.13
    🦳
    1.13
    👵
    1.13
    octo
    1.12
    Activations Density 0.037%

    No Known Activations