© 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. 10-GEMMASCOPE-RES-131K
    7. 42773
    Prev
    Next
    INDEX
    Explanations

    introduces conclusion or explanation

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

    The neuron fires on the discourse marker “So” used to begin or connect sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    kreises
    -1.70
    THERE
    -1.66
     “...
    -1.60
    If
    -1.59
     anser
    -1.57
    taglio
    -1.56
     THERE
    -1.55
    cloudf
    -1.55
    стере
    -1.55
                       
    -1.52
    POSITIVE LOGITS
    begin
    2.17
     again
    2.16
    end
    1.95
     actually
    1.90
     when
    1.90
     certainly
    1.70
     have
    1.59
     really
    1.58
     because
    1.56
     explain
    1.56
    Activations Density 0.013%

    No Known Activations