© 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. 22-GEMMASCOPE-RES-131K
    7. 38998
    Prev
    Next
    INDEX
    Explanations

    talent and recognition

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

    The neuron responds to words denoting exceptional ability or giftedness (e.g., “talent,” “talented,” “gifted,” “gifts,” etc.).

    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
    atika
    -0.95
    znam
    -0.94
    ctomy
    -0.93
     обви
    -0.89
    щения
    -0.89
    krati
    -0.88
    лях
    -0.86
    thaw
    -0.86
    vă
    -0.86
    ങ
    -0.85
    POSITIVE LOGITS
     should
    1.23
     but
    1.13
     Unfortunately
    1.08
     potential
    1.03
     talents
    1.02
    Unfortunately
    1.00
     talent
    0.98
    幸いです
    0.95
     who
    0.93
    可惜
    0.92
    Activations Density 0.053%

    No Known Activations