© 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. 36606
    Prev
    Next
    INDEX
    Explanations

    sending email and requests

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

    The neuron activates on mentions of follow‐up communications—e.g. sending or following up with emails or contacts.

    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
     客厅
    -1.30
    攷
    -1.13
     别墅
    -1.12
    ⚕
    -1.12
     argento
    -1.11
     quarta
    -1.09
     children
    -1.07
    軼
    -1.06
    ytale
    -1.05
    
    -1.05
    POSITIVE LOGITS
     email
    1.88
    ᾿
    1.66
     reply
    1.59
     contact
    1.54
     send
    1.45
     request
    1.41
     sends
    1.41
     sent
    1.40
     sending
    1.34
     your
    1.30
    Activations Density 0.032%

    No Known Activations