© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71388
    Prev
    Next
    INDEX
    Explanations

    Raleigh, Thursday, legal references

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

    The neuron strongly lights up on capitalized tokens—proper nouns or abbreviations (e.g. “Raleigh,” “Ex,” “Re,” “St.”)—marking section headings and named entities.

    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
     -¿
    -1.79
     convient
    -1.73
     sanoo
    -1.71
     vítimas
    -1.70
     cinto
    -1.64
     τὸν
    -1.64
     唯美
    -1.63
     Infór
    -1.63
     Tienen
    -1.60
     taxas
    -1.59
    POSITIVE LOGITS
     or
    1.91
          
    1.73
              
    1.66
     but
    1.66
           
    1.64
     general
    1.61
     e
    1.59
    re
    1.55
     M
    1.55
     different
    1.54
    Activations Density 0.000%

    No Known Activations