© 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. 66177
    Prev
    Next
    INDEX
    Explanations

    Memorandum Opinion

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

    The neuron detects occurrences of the word “memorandum,” especially in document headings or titles.

    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
     The
    -2.92
     They
    -2.81
     FROM
    -2.67
     다른
    -2.64
    他的
    -2.61
     We
    -2.58
     dari
    -2.53
     anderen
    -2.52
     But
    -2.48
     When
    -2.42
    POSITIVE LOGITS
    酲
    2.73
    呖
    2.70
    焄
    2.61
     Ottobre
    2.53
    馘
    2.50
    the
    2.39
    韞
    2.33
    thansa
    2.33
     він
    2.31
    vanju
    2.30
    Activations Density 0.005%

    No Known Activations