© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    sending or receiving messages

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

    The neuron strongly activates on header or metadata lines in correspondence (e.g. “To:,” “From:,” dates, “Dear,” “Subject,” 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_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
     anglaise
    -1.16
     tages
    -1.14
     winkel
    -1.12
     fabrik
    -1.11
     begon
    -1.09
     syk
    -1.08
    我們
    -1.07
     Gratis
    -1.02
     bottes
    -1.02
     fatale
    -1.02
    POSITIVE LOGITS
     your
    1.72
     gửi
    1.52
     sending
    1.51
     send
    1.43
     sends
    1.43
     again
    1.42
     reply
    1.41
     sent
    1.32
     letter
    1.29
     enviada
    1.22
    Activations Density 0.028%

    No Known Activations