© 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. 10-GEMMASCOPE-RES-131K
    7. 100469
    Prev
    Next
    INDEX
    Explanations

    U followed by abbreviation or punctuation

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

    The neuron selectively activates on the single uppercase “U” token, as used in abbreviations (e.g. U.S.), university names (e.g. U C S F), and similar contexts.

    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
    閙
    -1.58
     ebenfalls
    -1.54
    
    -1.53
    </em>
    -1.52
     hitherto
    -1.45
    自身の
    -1.45
     normalerweise
    -1.44
    过多
    -1.43
    篋
    -1.41
     имел
    -1.41
    POSITIVE LOGITS
    ржа
    1.61
    ilization
    1.60
    онов
    1.59
    ୈ
    1.57
     Novembre
    1.55
    檍
    1.52
     militer
    1.48
    滟
    1.44
    fect
    1.43
     européenne
    1.41
    Activations Density 0.039%

    No Known Activations