© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59940
    Prev
    Next
    INDEX
    Explanations

    founders and ceos

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

    The neuron fires strongly on personal names—especially high-profile founders, CEOs, and co-founders.

    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
     všechny
    -1.43
     your
    -1.33
     my
    -1.30
    wezen
    -1.28
     sogno
    -1.20
     desiderio
    -1.19
     всички
    -1.16
    geten
    -1.16
     sogni
    -1.15
     lettore
    -1.14
    POSITIVE LOGITS
    仅
    1.59
    僅
    1.36
     of
    1.23
     apenas
    1.14
    chrift
    1.14
    leder
    1.13
    нії
    1.13
        
    1.12
    </tr>
    1.10
     только
    1.09
    Activations Density 0.077%

    No Known Activations