© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77311
    Prev
    Next
    INDEX
    Explanations

    email headers and dates

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

    The neuron detects email header labels (e.g., “From:”, “To:”, “Cc:”, “Subject:”).

    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
    eturn
    -0.86
     PUBLICATION
    -0.84
     Pok
    -0.79
     Beta
    -0.76
    ',
    -0.75
    xiu
    -0.75
    撰
    -0.74
    LANTA
    -0.73
    omore
    -0.73
    imen
    -0.73
    POSITIVE LOGITS
    浪费
    0.89
    網址
    0.88
    老头
    0.88
    ¹.
    0.84
    ينج
    0.84
    REMARKS
    0.83
     包装
    0.82
     订单
    0.79
     PUST
    0.79
    Sekolah
    0.79
    Activations Density 0.007%

    No Known Activations