© 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. 91070
    Prev
    Next
    INDEX
    Explanations

    network IP addresses and ports

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

    The neuron selectively activates on numeric tokens and digit sequences (e.g. numbers in IPs, ports, counts, years, IDs).

    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
     too
    -0.81
     matrícula
    -0.77
    されると
    -0.76
     aimed
    -0.74
     demonstrated
    -0.72
     struck
    -0.70
     updateTime
    -0.70
     constituyen
    -0.70
    jména
    -0.70
     expressing
    -0.69
    POSITIVE LOGITS
     mask
    1.23
     Mask
    1.13
     masks
    1.06
     маска
    1.02
     MASK
    0.97
    mask
    0.95
    MASK
    0.93
    Mask
    0.91
     Masks
    0.90
     SOON
    0.86
    Activations Density 0.006%

    No Known Activations