© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16139
    Prev
    Next
    INDEX
    Explanations

    maiden names in parentheses

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

    The neuron activates on parenthetical biographical details—especially names, dates, and “née” maiden-name markers enclosed in parentheses.

    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
     optimale
    -1.15
    ꯝ
    -1.14
     verhind
    -1.14
    Poznám
    -1.12
    Vlast
    -1.09
    灵气
    -1.09
    Hlav
    -1.08
    ついに
    -1.07
    Obrázky
    -1.06
    назна
    -1.02
    POSITIVE LOGITS
     who
    1.16
     ebenfalls
    1.13
     of
    1.09
     langt
    1.04
     않
    1.02
    Тогда
    1.02
     женщина
    1.02
     født
    1.02
    koľ
    1.02
     شوهر
    1.00
    Activations Density 0.004%

    No Known Activations