© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6766
    Prev
    Next
    INDEX
    Explanations

    performance and events

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

    The neuron strongly activates on numeric tokens—dates, times, addresses, and other digit sequences 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
    年来
    -0.83
     سانتی
    -0.81
     fueran
    -0.79
     requête
    -0.76
    ufnahme
    -0.76
    字段
    -0.76
    ampiyon
    -0.76
    リス
    -0.75
    朝から
    -0.74
     peptides
    -0.73
    POSITIVE LOGITS
     performances
    2.50
     performance
    2.16
    Performances
    1.79
     Performances
    1.69
    Performance
    1.56
    performance
    1.56
     nightly
    1.54
     PERFORMANCE
    1.52
    公演
    1.44
    PERFORMANCE
    1.43
    Activations Density 0.026%

    No Known Activations