© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    origin-destination pairs

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

    The neuron detects descriptions of point-to-point (origin–destination) network connections or “pairs.”

    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
    illermo
    -0.83
    ungsbedingungen
    -0.73
     mechanisms
    -0.73
    вался
    -0.71
    fé
    -0.71
     advancement
    -0.71
    返信
    -0.69
    オススメです
    -0.68
     marrone
    -0.68
     mechanism
    -0.67
    POSITIVE LOGITS
     origin
    1.37
     demand
    1.33
     Origin
    1.31
     origins
    1.29
     OD
    1.27
     Origins
    1.27
     flows
    1.26
     traffic
    1.25
    origin
    1.23
    Origin
    1.20
    Activations Density 0.044%

    No Known Activations