© 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. 34-GEMMASCOPE-RES-131K
    7. 109442
    Prev
    Next
    INDEX
    Explanations

    Serena Williams

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

    The neuron strongly activates on proper names that begin with the letters “S-a-r-a/Ser-” (e.g. Serena, Sarachik, Saradidi, Serendipitous).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ayr
    -0.77
    veu
    -0.71
    },'
    -0.71
    telen
    -0.71
     halv
    -0.70
    vias
    -0.69
    features
    -0.69
    xfa
    -0.68
    ätz
    -0.68
    viato
    -0.68
    POSITIVE LOGITS
    ający
    0.75
    чески
    0.75
     Anterior
    0.73
     非
    0.73
    Quoting
    0.72
    ospels
    0.72
    ָד
    0.71
    roupe
    0.71
     coming
    0.71
    collating
    0.70
    Activations Density 0.025%

    No Known Activations