© 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. 10256
    Prev
    Next
    INDEX
    Explanations

    president names

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

    The neuron responds specifically to the proper name “Donald.”

    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
     卡
    -1.36
    毖
    -1.34
     آمد
    -1.26
    ,\\
    -1.26
     :).
    -1.24
     regler
    -1.23
    铪
    -1.23
     cilindro
    -1.23
    tuigen
    -1.23
    tiembre
    -1.22
    POSITIVE LOGITS
    go
    1.20
     become
    1.17
     Zukunft
    1.16
     no
    1.16
     he
    1.13
    ↵
    1.13
     there
    1.13
    1
    1.12
    ten
    1.11
    n
    1.09
    Activations Density 0.050%

    No Known Activations