© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40548
    Prev
    Next
    INDEX
    Explanations

    Reagan, Regan, Ragan, Obama

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

    The neuron activates on subword pieces that together spell out personal names (e.g. “Reagan,” “Regan,” “Obama,” “Meagan,” “Aila”), so it’s detecting people’s names.

    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
    </strong>
    -2.63
     workable
    -2.31
    
    -2.31
    莇
    -2.31
     possu
    -2.31
    ꪔ
    -2.28
    .,"
    -2.16
     Bestandteil
    -2.16
    无疑
    -2.08
     apont
    -2.08
    POSITIVE LOGITS
    </td>
    2.67
    𝐒
    2.31
    😱
    2.30
     ワールド
    2.19
    凜
    2.06
    U
    2.03
    a
    2.02
    ci
    2.00
    quilo
    1.99
    鏨
    1.99
    Activations Density 0.001%

    No Known Activations