© 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. 38757
    Prev
    Next
    INDEX
    Explanations

    Supporting Information

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

    This neuron detects section or file references labeled “Supporting Information.”

    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
    “
    -2.88
     '
    -2.81
     The
    -2.70
    
    -2.69
     Heilige
    -2.34
     harten
    -2.34
     geze
    -2.30
    럿
    -2.27
     nette
    -2.27
    ☆☆
    -2.25
    POSITIVE LOGITS
    玙
    2.67
    代わり
    2.58
    🡺
    2.50
    ஂ
    2.47
    曏
    2.45
     видит
    2.45
    ｃｍ
    2.36
    ୌ
    2.34
    迨
    2.34
     They
    2.31
    Activations Density 0.014%

    No Known Activations