© 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. 81705
    Prev
    Next
    INDEX
    Explanations

    licensing terms or code comments

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

    This neuron fires on capitalized technical and organizational terms—proper names like “TASS,” “National Institute for Health and Clinical Excellence,” software license names, UI component names, and similar identifiers.

    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
    dus
    -0.64
     энергии
    -0.64
     Zuh
    -0.63
     "./
    -0.63
    oma
    -0.63
    ftant
    -0.63
     bloating
    -0.62
    眯
    -0.62
     Hòa
    -0.62
     understatement
    -0.62
    POSITIVE LOGITS
     Topo
    0.79
     TOPOLOGY
    0.79
    หลวง
    0.73
    arwal
    0.69
    消息
    0.69
    botten
    0.68
    Topo
    0.68
     Houston
    0.67
    visning
    0.66
     Topology
    0.66
    Activations Density 0.048%

    No Known Activations