© 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. 45507
    Prev
    Next
    INDEX
    Explanations

    IP addresses and network terms

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

    The neuron is highly activated by numeric tokens—especially the octet‐style numbers (and placeholders) used in IPv4 address and range notation.

    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
     chiến
    -0.79
    合同
    -0.72
    anyag
    -0.72
    kosh
    -0.71
     автомобилей
    -0.71
    rucks
    -0.69
    ږ
    -0.69
    地点
    -0.69
     crops
    -0.69
     Ayuntamiento
    -0.68
    POSITIVE LOGITS
     subnet
    1.09
     quads
    0.90
    ('.')
    0.89
    ('.',
    0.87
    octet
    0.85
     redes
    0.84
     Network
    0.83
    Subnet
    0.82
    onen
    0.80
    網路
    0.80
    Activations Density 0.009%

    No Known Activations