© 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. 119571
    Prev
    Next
    INDEX
    Explanations

    kudos, swag, wiz, Stevie, Mav

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

    The neuron selectively activates on tokens that are written in uppercase or title‐case—e.g. brand names, acronyms, and other proper-noun identifiers.

    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
    ↵
    -4.44
     For
    -3.14
     After
    -3.05
    ve
    -3.05
     When
    -2.95
    0
    -2.89
    m
    -2.88
    $
    -2.75
    </em>
    -2.75
    )\
    -2.73
    POSITIVE LOGITS
    栊
    3.34
    硨
    3.30
     ausein
    3.28
    埽
    3.17
     rempliss
    3.14
    寕
    2.89
     soggior
    2.89
    鷙
    2.86
    
    2.84
    鲧
    2.80
    Activations Density 0.003%

    No Known Activations