© 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. 574
    Prev
    Next
    INDEX
    Explanations

    percentages following numbers

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

    The neuron fires on numeric characters or digit sequences (i.e. numbers) 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
     weeks
    -1.27
     week
    -1.13
    Weeks
    -0.88
     weekly
    -0.87
     Week
    -0.83
     Weeks
    -0.83
     WEEKS
    -0.82
     Quarters
    -0.82
    週間
    -0.81
    每周
    -0.81
    POSITIVE LOGITS
    บ
    0.70
    avx
    0.70
     senses
    0.70
     mema
    0.70
    祖
    0.69
     citrus
    0.69
    PACK
    0.69
    ڳ
    0.69
    ACK
    0.68
     STAR
    0.68
    Activations Density 0.049%

    No Known Activations