© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117646
    Prev
    Next
    INDEX
    Explanations

    sending or receiving communications

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

    The neuron is detecting references to written correspondence or communication items (e.g. letters, emails, notices, statements, comments).

    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
    riebenen
    -1.07
    شيخ
    -0.94
     simplistic
    -0.91
     発表
    -0.91
    DISE
    -0.90
     plausible
    -0.90
    Auszeichnungen
    -0.89
     dürfte
    -0.89
    Vehiculo
    -0.89
     пишет
    -0.88
    POSITIVE LOGITS
     about
    2.23
     stating
    2.06
     regarding
    2.02
     saying
    1.94
     telling
    1.75
     explaining
    1.75
     detailing
    1.74
     indicating
    1.73
     containing
    1.66
     asking
    1.63
    Activations Density 0.217%

    No Known Activations