© 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. 22-GEMMASCOPE-RES-131K
    7. 12662
    Prev
    Next
    INDEX
    Explanations

    also, others

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

    The neuron fires on adversative discourse markers (contrast words) such as “but” and “although.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vermutlich
    -0.97
     the
    -0.97
    :][
    -0.93
    太
    -0.93
    想到
    -0.87
     about
    -0.87
    最快更新
    -0.87
     kwietnia
    -0.85
    nitř
    -0.85
     絵
    -0.85
    POSITIVE LOGITS
     also
    2.56
     other
    2.08
     также
    1.91
    Also
    1.81
     también
    1.74
     також
    1.74
     também
    1.68
     även
    1.66
     גם
    1.55
     others
    1.55
    Activations Density 0.044%

    No Known Activations