© 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. 9404
    Prev
    Next
    INDEX
    Explanations

    Shirley names

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

    The neuron is strongly activated by occurrences of the proper name “Shirley.”

    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
    咴
    -3.00
     včetně
    -2.53
    何况
    -2.47
     pady
    -2.41
    他已经
    -2.41
    他会
    -2.33
    佧
    -2.31
    虽说
    -2.22
     thinks
    -2.20
     церкви
    -2.20
    POSITIVE LOGITS
    </h3>
    3.27
    1
    2.77
    }
    2.61
    <strong>
    2.44
    
    2.36
    al
    2.31
    The
    2.30
    看到
    2.28
    通过
    2.25
    攫
    2.23
    Activations Density 0.001%

    No Known Activations