© 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. 103132
    Prev
    Next
    INDEX
    Explanations

    Metro

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

    The neuron strongly activates on standalone numeric tokens (digits or numbers, especially those in dates, stats, or image captions).

    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
    ナー
    -0.83
    ului
    -0.82
     مؤرشف
    -0.80
    barten
    -0.77
    garh
    -0.74
    STRUCTION
    -0.73
    祝い
    -0.73
     проч
    -0.73
    jev
    -0.71
     способом
    -0.70
    POSITIVE LOGITS
    Metro
    1.18
    metro
    1.18
     Metro
    1.14
    METRO
    1.02
     metro
    0.93
    MORE
    0.92
     METRO
    0.83
     excepción
    0.81
    תיים
    0.79
     NTS
    0.75
    Activations Density 0.003%

    No Known Activations