© 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. 34-GEMMASCOPE-RES-131K
    7. 45374
    Prev
    Next
    INDEX
    Explanations

    anniversaries and significant dates

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

    The neuron activates on tokens related to dates of commemorations and anniversary celebrations.

    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
    observation
    -0.90
     despues
    -0.81
     Società
    -0.81
    生活的
    -0.80
     observation
    -0.79
     maquina
    -0.79
     Laissez
    -0.77
    Thursday
    -0.77
    Wednesday
    -0.76
    zeits
    -0.75
    POSITIVE LOGITS
     Defender
    0.98
     date
    0.97
     patron
    0.93
     defender
    0.92
     Constitution
    0.90
     independence
    0.89
     Defenders
    0.85
    Defender
    0.85
     Independence
    0.85
     anniversary
    0.85
    Activations Density 0.015%

    No Known Activations