© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91759
    Prev
    Next
    INDEX
    Explanations

    February and Valentine's Day

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

    The neuron specifically picks out numeric tokens and other number‐related items (dates, statistics, scores, etc.) in the text.

    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
     Christmas
    -1.91
    December
    -1.81
    Christmas
    -1.76
     December
    -1.66
     January
    -1.66
    January
    -1.54
    christmas
    -1.54
     CHRISTMAS
    -1.45
     новогод
    -1.42
     december
    -1.37
    POSITIVE LOGITS
     Feb
    2.14
     February
    1.99
    Feb
    1.82
     Valentine
    1.79
    February
    1.69
     февра
    1.66
     valentine
    1.64
     febrero
    1.62
     febbraio
    1.60
     février
    1.56
    Activations Density 0.074%

    No Known Activations