© 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. 22-GEMMASCOPE-RES-131K
    7. 9494
    Prev
    Next
    INDEX
    Explanations

    email 'From:' header

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

    the presence of email or message header markers (e.g. “From:”, “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_22/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
     there
    -0.94
     you
    -0.94
    stanze
    -0.87
     shown
    -0.86
     checked
    -0.82
    nora
    -0.81
     its
    -0.79
    ISCHE
    -0.77
    philly
    -0.76
     Datenbank
    -0.75
    POSITIVE LOGITS
    ๅ
    1.03
     applau
    1.02
     hiver
    0.99
     proie
    0.96
    揸
    0.96
    Nasc
    0.95
     remercier
    0.95
    ingresso
    0.95
     NKC
    0.93
    벡터
    0.92
    Activations Density 0.002%

    No Known Activations