© 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. 14445
    Prev
    Next
    INDEX
    Explanations

    French royalty, revolution, and places

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

    The neuron flags capitalized named entities—especially historical people, places, events, institutions, and date years—found in encyclopedic text.

    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
    琑
    -2.30
    ⎚
    -2.22
    ⩥
    -2.17
    
    -2.16
     hinder
    -2.16
    樒
    -2.11
     getItemId
    -2.09
     /\.(
    -2.08
    珖
    -2.02
     leitor
    -1.99
    POSITIVE LOGITS
    </h3>
    2.91
    ’
    2.72
    s
    2.64
    e
    2.22
    "
    2.02
    त
    2.02
    ↵↵
    1.99
    h
    1.89
    U
    1.84
     for
    1.83
    Activations Density 0.012%

    No Known Activations