© 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. 124054
    Prev
    Next
    INDEX
    Explanations

    email replies or personal statements

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

    The neuron detects reply‐attribution markers in email or forum quotes—specifically the “wrote:” lines that introduce quoted text.

    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
    '
    -2.31
    ,
    -2.11
    (
    -1.84
     perú
    -1.78
    tedì
    -1.77
     moreno
    -1.68
     vernie
    -1.60
     chèvre
    -1.59
     réservation
    -1.55
     Ottobre
    -1.54
    POSITIVE LOGITS
    </i>
    2.73
     $
    2.20
    TryDecode
    2.00
    </strong>
    1.96
    })$
    1.85
    y
    1.84
    derdag
    1.80
    ↵
    1.78
    ppuden
    1.77
    整个
    1.77
    Activations Density 0.003%

    No Known Activations