© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33121
    Prev
    Next
    INDEX
    Explanations

    Xanthomonas, Zandvoort, Zaner

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

    names or words containing 'z' followed by vowels like "zan", "zañ", "zand", "zang", or "xanth".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to tokens containing the substring “zan” (e.g. in Zaner, Zanussi, Zañartu, Zandvoort, Zanesville, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Meksiko
    -0.94
    以内
    -0.82
     Profesional
    -0.82
    ✠
    -0.80
     概要
    -0.77
    митрий
    -0.74
     rectified
    -0.73
     apparti
    -0.73
     誰
    -0.73
    Struktur
    -0.73
    POSITIVE LOGITS
     Merry
    0.75
    吏
    0.72
    setBackground
    0.72
    
    0.70
     Zan
    0.68
     Sewell
    0.68
     dezembro
    0.67
    tiveness
    0.66
    Merry
    0.65
     Blood
    0.65
    Activations Density 0.022%

    No Known Activations