© 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. 10-GEMMASCOPE-RES-131K
    7. 105691
    Prev
    Next
    INDEX
    Explanations

    quadruple burden

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

    The neuron is sensitive to programming identifiers or code names (e.g. package or variable names, camelCase or uppercase‐underscore tokens).

    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
    쐈
    -2.13
     carrés
    -1.76
    컹
    -1.73
    킁
    -1.73
    俛
    -1.73
     éché
    -1.72
     QUÉ
    -1.72
     Améli
    -1.70
     Atención
    -1.68
    
    -1.68
    POSITIVE LOGITS
     with
    2.67
     in
    2.31
     by
    2.14
     for
    2.14
     all
    1.92
     even
    1.78
     between
    1.76
     a
    1.74
     through
    1.74
     on
    1.73
    Activations Density 0.001%

    No Known Activations