© 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. 34-GEMMASCOPE-RES-131K
    7. 86919
    Prev
    Next
    INDEX
    Explanations

    sending messages or items

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

    The neuron activates strongly on various forms of the verb “send” (send, sent, sending).

    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
     οποία
    -1.05
    вість
    -1.00
     decoradas
    -1.00
    Figur
    -0.94
    Clicks
    -0.89
    runchy
    -0.88
    移動
    -0.88
     decorados
    -0.87
     ذکر
    -0.86
    τσα
    -0.85
    POSITIVE LOGITS
     send
    1.80
     sends
    1.78
     Send
    1.70
     envía
    1.70
    Send
    1.61
     a
    1.59
     sending
    1.58
     Sending
    1.53
     发送
    1.52
     forth
    1.49
    Activations Density 0.018%

    No Known Activations