© 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. 22-GEMMASCOPE-RES-131K
    7. 98626
    Prev
    Next
    INDEX
    Explanations

    female names followed by surnames

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

    The neuron strongly activates on personal proper names (people’s names) in the biographical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    撰文
    -0.99
    ()]);
    -0.95
    久しぶりに
    -0.93
    tvguidetime
    -0.93
     stessi
    -0.92
    ついに
    -0.91
    فوائد
    -0.91
    ärt
    -0.91
     واضح
    -0.91
     गणना
    -0.90
    POSITIVE LOGITS
     who
    1.25
     other
    1.02
    rew
    0.97
    ఝ
    0.94
     it
    0.94
     остальных
    0.91
     ресурсов
    0.91
     obud
    0.90
     quelqu
    0.90
    REPLY
    0.88
    Activations Density 0.031%

    No Known Activations