© 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. 19840
    Prev
    Next
    INDEX
    Explanations

    Jameson, Paxton, Rens, hemophilia

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

    names of people or program identifiers in technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on uncommon multi‐syllable names and specialized proper‐noun–style tokens (e.g. people’s names, place names, chemical or technical terms).

    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
    ⃚
    -3.48
    ⬮
    -3.42
    
    -3.16
    pecabe
    -3.16
    寕
    -3.09
    ﮩ
    -2.95
    鯔
    -2.92
    ﮧ
    -2.92
    蒾
    -2.88
    褡
    -2.81
    POSITIVE LOGITS
     
    3.00
      
    2.83
       
    2.72
         
    2.72
          
    2.67
     {
    2.66
     he
    2.56
                    
    2.53
     той
    2.45
    ">
    2.34
    Activations Density 0.015%

    No Known Activations