© 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. 102554
    Prev
    Next
    INDEX
    Explanations

    prestige and prestigiousness

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

    The neuron primarily detects occurrences of the word “prestige” (and its form “prestigious”).

    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
    this
    -2.72
    ⟝
    -2.44
    艄
    -2.31
     $
    -2.30
     ‚
    -2.23
    擼
    -2.23
    驩
    -2.22
    銲
    -2.17
     judíos
    -2.16
    ⏑
    -2.14
    POSITIVE LOGITS
     cuaca
    2.14
    ’
    2.11
    </b>
    2.03
    талия
    1.98
    Специ
    1.97
     parfü
    1.96
    伦敦
    1.95
    e
    1.92
     behövs
    1.91
    Knowing
    1.91
    Activations Density 0.003%

    No Known Activations