© 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. 22-GEMMASCOPE-RES-131K
    4. 69133
    Prev
    Next
    INDEX
    Explanations

    favorable

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

    The neuron fires on discourse‐structuring and emphasis tokens—conjunctions, transitions, and emphasis markers that signal how sentences are connected or highlighted.

    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
     some
    -1.12
     things
    -1.09
     certainly
    -1.09
     possibly
    -1.05
     actually
    -1.04
     practically
    -0.99
     perhaps
    -0.99
     様
    -0.98
     considerably
    -0.98
     substantially
    -0.96
    POSITIVE LOGITS
     található
    1.13
    thumbsup
    1.01
     Đó
    0.98
     óra
    0.96
     zupeł
    0.95
     összefoglaló
    0.94
    tagez
    0.94
     Chủ
    0.94
     kovo
    0.93
     Những
    0.92
    Activations Density 0.001%

    No Known Activations