© 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. 65382
    Prev
    Next
    INDEX
    Explanations

    Bobby and associated names

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

    The neuron consistently activates on the proper name “Bobby.”

    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
    '
    -3.02
     '
    -2.58
    🕗
    -2.56
    里有
    -2.52
     ('
    -2.47
     is
    -2.41
    !"
    -2.25
     Businesses
    -2.20
    ние
    -2.20
     The
    -2.20
    POSITIVE LOGITS
     ſte
    3.56
    1
    3.06
    ”-
    2.83
    罴
    2.81
    ?”
    2.75
    :”
    2.70
    The
    2.70
    ”:
    2.66
    㐂
    2.59
    Ꭳ
    2.58
    Activations Density 0.001%

    No Known Activations