© 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. 118982
    Prev
    Next
    INDEX
    Explanations

    Carmen followed by names. EGFR and FFA in biology

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

    The neuron activates for the name "Carmen" in text, with stronger activations for instances where it appears as a personal name rather than in other contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    萏
    -2.67
     fazem
    -2.66
     terão
    -2.50
    “
    -2.48
     setelan
    -2.48
    ኧ
    -2.47
     serão
    -2.44
     tinham
    -2.41
    ௅
    -2.41
    狁
    -2.38
    POSITIVE LOGITS
     revolves
    2.42
     has
    2.39
     It
    2.36
     seems
    2.33
     o
    2.33
    変わ
    2.30
     seven
    2.27
     enjoys
    2.27
    ?’
    2.27
     discovered
    2.25
    Activations Density 0.003%

    No Known Activations