© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84813
    Prev
    Next
    INDEX
    Explanations

    abundance and opportunities

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

    The neuron responds to idiomatic quantifier expressions—especially hyperbolic abundance or scarcity phrases (e.g. “shortage of,” “galore,” “more than you can shake a stick at”).

    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
              
    -1.23
    та
    -1.20
     dons
    -1.17
    $
    -1.15
     jPanel
    -1.15
           
    -1.15
     quoc
    -1.13
     deß
    -1.12
    شنبه
    -1.10
     oras
    -1.10
    POSITIVE LOGITS
     opportunities
    1.48
     opportunity
    1.24
     pôr
    1.23
    躊
    1.23
     aporte
    1.20
    身の
    1.17
     prefeito
    1.16
     plenty
    1.16
    違和
    1.15
     mês
    1.13
    Activations Density 0.028%

    No Known Activations