© 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. 59300
    Prev
    Next
    INDEX
    Explanations

    Internet domains and measurements

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

    This neuron activates on standalone numeric tokens—especially version numbers, IP-like or digit‐heavy identifiers in technical/configuration 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
     FDA
    -0.73
     искус
    -0.71
     CBA
    -0.71
    мії
    -0.70
    钥
    -0.70
    PCell
    -0.69
     parmesan
    -0.68
     gepub
    -0.68
     berada
    -0.68
     водо
    -0.67
    POSITIVE LOGITS
     peering
    1.17
     IPv
    1.00
     Internet
    0.98
    Internet
    0.92
     DDoS
    0.90
     Measurements
    0.89
     ripen
    0.88
    Measurements
    0.84
     Dante
    0.84
    measurements
    0.83
    Activations Density 0.051%

    No Known Activations