© 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. 22-GEMMASCOPE-RES-131K
    7. 40388
    Prev
    Next
    INDEX
    Explanations

    entrepreneurship, entrepreneurialism

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

    The neuron fires on occurrences of the root “entrepreneur” and its derivatives (entrepreneurship, entrepreneurial, 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
    ll
    -2.50
     et
    -2.39
    絎
    -2.22
    籥
    -2.20
    嘥
    -2.11
    );
    -2.06
    out
    -2.06
    -2.06
    2
    -2.05
     intric
    -2.03
    POSITIVE LOGITS
     书法
    2.30
    婓
    2.30
    涣
    2.30
    沇
    2.16
     水墨
    2.16
    鹟
    2.11
    
    2.09
    焿
    2.06
    缜
    2.05
    鏵
    2.03
    Activations Density 0.006%

    No Known Activations