© 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. 25967
    Prev
    Next
    INDEX
    Explanations

    unless otherwise exception

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

    The neuron detects boilerplate legal exception phrases (e.g. “except where otherwise noted” or “unless otherwise indicated”).

    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
    kler
    -0.94
    henswürdigkeiten
    -0.92
    Màu
    -0.89
     навіть
    -0.86
    Напомним
    -0.85
     montón
    -0.85
    Kast
    -0.85
     setelah
    -0.83
    一样的
    -0.82
    سوال
    -0.82
    POSITIVE LOGITS
     otherwise
    1.63
     contrary
    1.41
     noted
    1.38
    另
    1.31
     stated
    1.30
     inaczej
    1.28
     anders
    1.23
     exceptions
    1.21
     specify
    1.20
     elsewhere
    1.19
    Activations Density 0.044%

    No Known Activations