© 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. 110936
    Prev
    Next
    INDEX
    Explanations

    start of structured text

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

    The neuron fires on occurrences of the specific two‐letter sequence “gz.”

    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
    .
    -1.60
    ))^
    -1.56
    ى
    -1.55
     to
    -1.52
     ผม
    -1.50
    часы
    -1.49
     Aquí
    -1.49
     &
    -1.47
    !
    -1.46
    䜣
    -1.45
    POSITIVE LOGITS
    henswürdigkeiten
    1.79
    Those
    1.77
    ších
    1.76
    vantaged
    1.74
     huset
    1.63
     giyim
    1.63
    That
    1.59
     parfüm
    1.54
    Having
    1.53
    s
    1.51
    Activations Density 0.000%

    No Known Activations