© 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. 58052
    Prev
    Next
    INDEX
    Explanations

    reciprocal interaction between entities

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

    The neuron detects words that describe linking or communication between components (e.g. connect, communicate, linked, networked).

    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
     its
    -1.14
    它的
    -1.02
     его
    -0.99
     отдельно
    -0.93
     accompanying
    -0.92
     itself
    -0.91
     surrounded
    -0.90
    它
    -0.87
     jego
    -0.82
    its
    -0.82
    POSITIVE LOGITS
     miteinander
    2.33
     друг
    2.22
     eachother
    1.98
     birbir
    1.87
    กัน
    1.80
     each
    1.79
     nhau
    1.78
    彼此
    1.67
    互相
    1.67
     together
    1.57
    Activations Density 0.084%

    No Known Activations