© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86046
    Prev
    Next
    INDEX
    Explanations

    magnetization, resuscitation, developed, holiday, profile

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

    The neuron is looking for long, technical noun forms—especially those ending in “-ation” or “-ization.”

    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
     postgres
    -1.51
     oub
    -1.50
    他们
    -1.41
     pengar
    -1.38
    沒有
    -1.38
     منزل
    -1.34
     Chambres
    -1.34
     maxime
    -1.33
    时间
    -1.31
    他們
    -1.30
    POSITIVE LOGITS
     even
    2.38
     as
    2.14
     in
    2.09
     навіть
    1.93
     that
    1.87
     by
    1.83
     to
    1.83
     on
    1.76
     such
    1.71
     incluso
    1.66
    Activations Density 0.186%

    No Known Activations