© 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. 58512
    Prev
    Next
    INDEX
    Explanations

    prize for

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

    The neuron fires on mentions of prizes or awards (e.g. “Prize,” “Nobel,” “award,” and their associated numeric values).

    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
    
    -1.91
     stubbornly
    -1.83
    ︕
    -1.77
    zędu
    -1.75
     jokingly
    -1.70
    Ꭳ
    -1.69
     anxiously
    -1.68
     affectionately
    -1.68
     bê
    -1.66
     éti
    -1.66
    POSITIVE LOGITS
    s
    1.80
    A
    1.77
     for
    1.63
     to
    1.49
     et
    1.48
     by
    1.39
    JE
    1.38
    0
    1.38
    人也
    1.37
     '['
    1.35
    Activations Density 0.018%

    No Known Activations