© 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. 84968
    Prev
    Next
    INDEX
    Explanations

    female first names followed by words

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

    The neuron specifically fires on occurrences of the proper name “Carolyn.”

    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
    籐
    -3.53
    ).
    -3.25
    䊐
    -2.88
    灩
    -2.70
    vantaged
    -2.64
    熨
    -2.63
    山中
    -2.56
    镭
    -2.56
    ]["
    -2.48
    錘
    -2.48
    POSITIVE LOGITS
    1
    4.84
    2
    4.28
    4
    4.03
    3
    3.95
    6
    3.72
    9
    3.69
    7
    3.42
    5
    3.41
    with
    3.27
    8
    3.16
    Activations Density 0.005%

    No Known Activations