© 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. 99395
    Prev
    Next
    INDEX
    Explanations

    Spain, Spanish, historical figures

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

    This neuron detects numeric tokens, especially years and date-related 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
     Darío
    -0.77
     plagio
    -0.73
    Estudio
    -0.70
    BENEF
    -0.70
     Tokio
    -0.70
    destiny
    -0.69
     Rimini
    -0.69
    ৗ
    -0.68
    頭痛
    -0.68
     crema
    -0.68
    POSITIVE LOGITS
     Spain
    1.13
    Spain
    1.10
     Spanish
    1.02
    Spanish
    1.02
    Carlos
    0.96
     Carlos
    0.90
     Habs
    0.89
     испан
    0.82
    啤
    0.82
    西班牙
    0.82
    Activations Density 0.023%

    No Known Activations