© 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. 48483
    Prev
    Next
    INDEX
    Explanations

    references to table

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

    The neuron fires on in‐text table references (e.g. “Table X”)—i.e. mentions of tables by their number in academic 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_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
     одним
    -1.66
    ommation
    -1.63
     {
    -1.59
     

    -1.57
    撰文
    -1.55
                 
    -1.55
     Да
    -1.55
           
    -1.55
     What
    -1.52
         
    -1.52
    POSITIVE LOGITS
     användas
    1.72
    된
    1.69
    le
    1.64
     tetapi
    1.55
    »،
    1.52
     egenskaper
    1.52
     Enero
    1.52
     PROBLE
    1.50
    見つ
    1.50
    e
    1.48
    Activations Density 0.002%

    No Known Activations