© 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. 91812
    Prev
    Next
    INDEX
    Explanations

    emails aresent

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

    This neuron fires on messaging-related terms and technical tokens—things like “text,” “messages,” “SMS,” “inbox,” “outbox,” “SMTP,” “Mailer,” etc.—i.e. references to email/SMS messaging systems and protocols.

    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
    шение
    -0.82
    wold
    -0.78
     releases
    -0.75
    atoday
    -0.75
    <0x81>
    -0.75
     aasta
    -0.74
     SSA
    -0.73
     Rick
    -0.72
    aneity
    -0.70
     cập
    -0.70
    POSITIVE LOGITS
     sent
    2.58
    Sent
    2.33
     Sent
    2.28
    sent
    2.25
     sending
    2.06
    SENT
    1.88
     send
    1.87
    Sending
    1.85
     SENT
    1.83
     Sending
    1.76
    Activations Density 0.063%

    No Known Activations